© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78779
    Prev
    Next
    INDEX
    Explanations

    enabler

    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_0_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
    ě
    1.52
    と
    1.34
    ە
    1.32
    ین
    1.30
    ৬
    1.30
    Ｉ
    1.27
    다라고
    1.23
    ৮
    1.19
    は
    1.18
    лю
    1.17
    POSITIVE LOGITS
    s
    1.64
    .
    1.56
    at
    1.45
    w
    1.38
    ियों
    1.32
    ?
    1.30
    ك
    1.29
    ar
    1.28
    xt
    1.27
     of
    1.26
    Activations Density 0.000%

    No Known Activations