© 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. 13539
    Prev
    Next
    INDEX
    Explanations

    parentheses and quotes enclosing or near code patterns

    oai_token-act-pair · gemini-2.0-flash

    )

    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
     Anſ
    -3.14
     myſelf
    -3.09
     itſelf
    -3.09
     Houſe
    -3.05
     Theſe
    -2.97
     Reſ
    -2.97
     Monfieur
    -2.95
     Efq
    -2.91
     pleaſure
    -2.88
     ſtate
    -2.84
    POSITIVE LOGITS
     and
    2.02
     
    1.92
     (
    1.86
     in
    1.84
     a
    1.75
    ,
    1.68
    ↵↵
    1.63
     A
    1.59
     the
    1.59
     "
    1.59
    Activations Density 4.070%

    No Known Activations