© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5520
    Prev
    Next
    INDEX
    Explanations

    cliches and idioms

    oai_token-act-pair · gemini-2.0-flash

    Finish line/race

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Diweddarwch
    -0.57
    مصادر
    -0.56
    Datuak
    -0.55
    ViewImports
    -0.47
    Примечания
    -0.47
     تخت
    -0.47
    Eloquent
    -0.46
     stimmen
    -0.45
     Eink
    -0.45
    Билгалдахарш
    -0.45
    POSITIVE LOGITS
     race
    0.96
     finish
    0.88
     FINISH
    0.84
     marathon
    0.83
    marathon
    0.77
     races
    0.75
    finish
    0.74
     Race
    0.74
    Race
    0.74
     Finish
    0.74
    Activations Density 0.720%

    No Known Activations