© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13392
    Prev
    Next
    INDEX
    Explanations

    the word "adult" and sometimes "childhood"

    oai_token-act-pair · gemini-2.0-flash

    adult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.65
     and
    -0.63
    LayoutStyle
    -0.62
     the
    -0.59
    '
    -0.57
     also
    -0.55
     was
    -0.52
    ↵↵
    -0.52
    entang
    -0.52
    IsMutable
    -0.50
    POSITIVE LOGITS
    出版年
    0.93
     Houſe
    0.85
     houſe
    0.76
     ſever
    0.71
     ſmall
    0.69
     Facult
    0.68
    PostExecute
    0.68
     faſt
    0.68
     defa
    0.65
    allowNull
    0.64
    Activations Density 1.524%

    No Known Activations