© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43829
    Prev
    Next
    INDEX
    Explanations

    tolerance

    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
    ↵↵
    0.85
    ur
    0.80
    us
    0.80
    ल
    0.79
    ot
    0.77
    س
    0.77
    os
    0.74
    лната
    0.71
    èque
    0.68
    지
    0.66
    POSITIVE LOGITS
    1.20
     I
    0.73
     رسمي
    0.73
    sd
    0.72
     on
    0.70
    限于
    0.70
    ^{-}
    0.69
     erfol
    0.68
     schrieb
    0.68
     опубликова
    0.66
    Activations Density 0.001%

    No Known Activations