© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    lines of code with color definitions

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    StructEnd
    -0.73
    Билгалдахарш
    -0.67
    :✨
    -0.67
    SharedCtor
    -0.64
    eleste
    -0.64
    tecs
    -0.62
    <thead>
    -0.60
    省市镇
    -0.60
    dores
    -0.60
    клопе
    -0.60
    POSITIVE LOGITS
     Lanz
    0.47
     fallait
    0.43
    pegno
    0.42
    NextToken
    0.40
     appunt
    0.40
     vouloir
    0.40
     gravid
    0.39
    MONG
    0.39
    쇄
    0.38
     rRNA
    0.38
    Activations Density 1.156%

    No Known Activations