© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14985
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as "public", "void", conditionals, comments, and fields

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    InitVars
    -0.94
    脚注の使い方
    -0.73
     esternos
    -0.68
     concernés
    -0.68
     ब्रेकडाउन
    -0.66
     estekak
    -0.66
     utafitiHapana
    -0.65
    Datuak
    -0.64
     BoxFit
    -0.64
     fallu
    -0.64
    POSITIVE LOGITS
    pogon
    0.42
    onAttach
    0.40
    ährung
    0.39
    noscript
    0.38
    pewa
    0.37
    He
    0.35
     maris
    0.35
    就这样
    0.35
    OwnProperty
    0.35
     embar
    0.35
    Activations Density 7.437%

    No Known Activations