© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49949
    Prev
    Next
    INDEX
    Explanations

    al-

    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_10_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
    ül
    0.48
    INE
    0.46
    TY
    0.46
     плану
    0.46
    ilever
    0.46
    I
    0.46
    üt
    0.45
    İM
    0.45
    iums
    0.45
     lures
    0.45
    POSITIVE LOGITS
    in
    0.55
     copol
    0.52
    s
    0.52
     of
    0.48
    لوب
    0.46
    ol
    0.45
    ≧
    0.45
     {{{
    0.44
     svůj
    0.44
    愣
    0.44
    Activations Density 0.010%

    No Known Activations