© 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. 15276
    Prev
    Next
    INDEX
    Explanations

    proper names, often first names

    oai_token-act-pair · gemini-2.0-flash

    names and proper nouns

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

    Names

    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
    IntoConstraints
    -0.78
    InvalidProtocol
    -0.76
    modelBuilder
    -0.74
     ModelExpression
    -0.72
     >=",
    -0.64
    }}/>
    -0.63
     createState
    -0.59
    parsedMessage
    -0.58
    ipot
    -0.57
    antMatchers
    -0.57
    POSITIVE LOGITS
     disambiguazione
    0.52
     Ekim
    0.51
    saraba
    0.49
     ansatte
    0.48
     imperio
    0.46
     potrivit
    0.46
    laku
    0.46
     Hok
    0.45
     Zauber
    0.45
     Kemal
    0.44
    Activations Density 1.244%

    No Known Activations