© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1873
    Prev
    Next
    INDEX
    Explanations

    sentences that express amazement or surprise, often in the context of an anecdote or personal experience, sometimes accompanied by a conjunction and a consequential factual observation

    oai_token-act-pair · gemini-2.0-flash

    emotional reactions and responses

    np_token-act-pair-logits · gpt-4o-mini

    emotional reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.62
     Bosque
    -0.61
    ParallelGroup
    -0.58
    ManagedBean
    -0.57
    lgari
    -0.56
    anthrene
    -0.56
     baffled
    -0.54
     distressed
    -0.53
    Географиясе
    -0.53
    RegressionTest
    -0.53
    POSITIVE LOGITS
    VersionUID
    0.56
     by
    0.53
     CHAPITRE
    0.50
     AssemblyTitle
    0.49
     to
    0.49
     muhte
    0.45
    δας
    0.45
     الاطلاع
    0.44
    saraba
    0.43
    最快更新
    0.43
    Activations Density 3.555%

    No Known Activations