© 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. 39279
    Prev
    Next
    INDEX
    Explanations

    Japanese names and suffixes

    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
     on
    0.71
    TO
    0.67
    Ö
    0.61
     gă
    0.60
     and
    0.58
     forearm
    0.56
    İ
    0.56
    瑯
    0.56
     east
    0.55
     сле
    0.55
    POSITIVE LOGITS
    ur
    0.95
    e
    0.78
    ed
    0.78
    t
    0.77
    an
    0.77
    o
    0.77
    r
    0.77
    ر
    0.76
    দের
    0.75
    ர்
    0.75
    Activations Density 0.000%

    No Known Activations