© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112321
    Prev
    Next
    INDEX
    Explanations

    URL query parameters

    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_2_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
     from
    0.57
     have
    0.57
     ড
    0.55
     at
    0.52
    elijke
    0.50
     in
    0.49
    **)
    0.47
    <\
    0.47
     französ
    0.47
     hoch
    0.46
    POSITIVE LOGITS
    し
    0.68
    де
    0.65
    t
    0.60
    N
    0.58
    ηση
    0.55
    اتی
    0.55
    一
    0.52
    ления
    0.52
    ён
    0.51
    는데
    0.51
    Activations Density 0.000%

    No Known Activations