© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11937
    Prev
    Next
    INDEX
    Explanations

    references or citations in scientific format

    oai_token-act-pair · gemini-2.0-flash

    fifth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Nine
    -0.59
     Ten
    -0.56
     nine
    -0.52
     ba
    -0.50
     NINE
    -0.47
    Ten
    -0.47
     nueve
    -0.47
    9
    -0.47
     ten
    -0.46
    migrationBuilder
    -0.45
    POSITIVE LOGITS
     fifth
    0.72
     FIFTH
    0.70
    五
    0.66
     Fifth
    0.64
    Fifth
    0.63
    ⑤
    0.63
     ویکی‌پدیا
    0.60
     fifties
    0.60
    ]';
    0.60
    fifth
    0.60
    Activations Density 1.624%

    No Known Activations