© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86397
    Prev
    Next
    INDEX
    Explanations

    tri- or mon- prefixes

    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_3_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
    ка
    0.80
    P
    0.77
    𝜁
    0.73
    A
    0.73
    I
    0.72
    G
    0.70
    D
    0.68
    ای
    0.67
    ᱫ
    0.67
     to
    0.66
    POSITIVE LOGITS
    。
    1.14
     It
    0.91
    ।
    0.87
    。</
    0.75
     presiden
    0.70
     Kaf
    0.69
     Mon
    0.67
     Tri
    0.67
    ीय
    0.65
     Generale
    0.65
    Activations Density 0.000%

    No Known Activations