© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31205
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     საბ
    0.37
    {//
    0.36
    umboldt
    0.36
    "("
    0.36
    Repeating
    0.36
     *}(
    0.35
    ropic
    0.33
    안녕하십니까
    0.33
    שוט
    0.33
     ["[
    0.33
    POSITIVE LOGITS
    ्यूम
    0.39
     ಸರ
    0.38
     lie
    0.37
     Politik
    0.37
     Plea
    0.36
     MATTER
    0.36
    汙
    0.36
    ަކ
    0.35
     Prosecution
    0.35
     Ane
    0.35
    Activations Density 0.010%

    No Known Activations