© 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. 14031
    Prev
    Next
    INDEX
    Explanations

    strings in code or configuration file contexts

    oai_token-act-pair · gemini-2.0-flash

    quotation marks/parentheses

    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
     تضيفلها
    -0.71
    tagHelperRunner
    -0.66
     nakalista
    -0.61
     كومونز
    -0.60
    Hochspringen
    -0.60
     مشين
    -0.57
     Babel
    -0.57
     TextInputType
    -0.56
    nvarchar
    -0.56
    Referències
    -0.56
    POSITIVE LOGITS
    <bos>
    0.61
    agrama
    0.49
    المشاركات
    0.48
    ifiquement
    0.46
    :✨
    0.46
    DeclareMath
    0.46
     the
    0.45
    دانشنامهٔ
    0.43
    hoeddwyd
    0.43
    ΑΙ
    0.43
    Activations Density 2.773%

    No Known Activations