© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4909
    Prev
    Next
    INDEX
    Explanations

    characters used in JSON files for date structures

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -2.58
     myſelf
    -2.20
     Monfieur
    -2.09
     itſelf
    -2.06
     Efq
    -1.98
     Theſe
    -1.89
     Jefus
    -1.80
     auffi
    -1.79
     raiſ
    -1.77
     ſever
    -1.75
    POSITIVE LOGITS
    ,
    1.34
    .
    1.13
     (
    1.13
     
    1.12
    :
    1.03
     or
    0.96
     in
    0.95
    /
    0.94
     -
    0.93
     “
    0.91
    Activations Density 2.388%

    No Known Activations