© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201596
    Prev
    Next
    INDEX
    Explanations

    photo and film

    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_46_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
     फ्लैट
    0.42
    去
    0.40
    Wr
    0.39
     Goes
    0.39
    Went
    0.38
    getRequest
    0.38
    レポート
    0.38
     flat
    0.37
    pull
    0.37
     अम
    0.37
    POSITIVE LOGITS
     अन्तर
    0.41
    麻煩
    0.40
     حركة
    0.38
    errno
    0.38
     lac
    0.38
     opal
    0.37
    唢
    0.37
    স্তর
    0.37
     Juicy
    0.37
    Ꮳ
    0.37
    Activations Density 0.000%

    No Known Activations