© 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. 38149
    Prev
    Next
    INDEX
    Explanations

    package main

    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
    و
    0.81
    ι
    0.73
    터
    0.68
    ्य
    0.64
    ام
    0.63
    ن
    0.63
    ким
    0.62
    ни
    0.59
    ា
    0.59
    두
    0.59
    POSITIVE LOGITS
     bulunduğu
    0.69
    the
    0.69
     kleiner
    0.65
    ชั่น
    0.63
    OD
    0.62
     kompakt
    0.62
    ية
    0.61
     Compact
    0.61
    -
    0.61
     compact
    0.59
    Activations Density 0.017%

    No Known Activations