© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80863
    Prev
    Next
    INDEX
    Explanations

    tech company platforms and services

    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_31_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
     cex
    0.33
    ništ
    0.31
     नर्मदा
    0.31
    නු
    0.30
    鰍
    0.30
    国有
    0.30
    ستگی
    0.30
     जौ
    0.30
     коды
    0.28
     ингреди
    0.28
    POSITIVE LOGITS
    PHOTO
    0.35
    photo
    0.31
    stad
    0.31
    Google
    0.30
    PARENT
    0.30
    beta
    0.30
     Google
    0.30
     France
    0.30
    randomIndex
    0.30
    氧
    0.30
    Activations Density 0.000%

    No Known Activations