© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173942
    Prev
    Next
    INDEX
    Explanations

    function calls and closures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     об
    0.48
    следование
    0.46
     екс
    0.44
     الب
    0.43
    IUM
    0.43
     الس
    0.42
    𝙃
    0.42
    IFICATION
    0.42
    を見る
    0.42
    溲
    0.42
    POSITIVE LOGITS
    media
    0.48
    plain
    0.48
    gard
    0.47
    com
    0.47
    hor
    0.47
    เพื่อ
    0.47
    and
    0.47
    fill
    0.46
    fields
    0.46
    gun
    0.46
    Activations Density 0.000%

    No Known Activations