© 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. 15513
    Prev
    Next
    INDEX
    Explanations

    imperative verbs and phrases requesting interaction

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns

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

    Imperative verbs

    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
    Negative Logits
     decompose
    -0.63
     specify
    -0.61
     designate
    -0.61
    numerusform
    -0.58
     autorytatywna
    -0.58
     perceive
    -0.57
    ModelAdmin
    -0.56
    曖昧さ回避
    -0.56
     denote
    -0.56
     reject
    -0.55
    POSITIVE LOGITS
     my
    0.68
     us
    0.60
     me
    0.60
     the
    0.58
     these
    0.54
     meille
    0.52
    holdt
    0.50
     our
    0.50
     some
    0.50
     this
    0.50
    Activations Density 3.092%

    No Known Activations