© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31226
    Prev
    Next
    INDEX
    Explanations

    component, staple, synonym, color, method, soundtrack, function

    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_40_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
    肠
    0.37
    षिक
    0.33
    所示
    0.33
    olefin
    0.33
     tą
    0.33
    RENCH
    0.32
     demikian
    0.32
     잔
    0.32
     ia
    0.31
     Tropic
    0.31
    POSITIVE LOGITS
    នៃ
    0.49
     của
    0.48
     của
    0.47
     ofthe
    0.47
     של
    0.46
     بتاعت
    0.41
    ของ
    0.39
    ของผู้
    0.38
     بتاع
    0.38
    ofthe
    0.38
    Activations Density 0.190%

    No Known Activations