© 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. 124686
    Prev
    Next
    INDEX
    Explanations

    text overlay

    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
     (
    0.71
    an
    0.70
    न
    0.68
    ’
    0.64
    ;
    0.62
     couv
    0.61
     sprawd
    0.59
    i
    0.59
     segreg
    0.57
     indag
    0.56
    POSITIVE LOGITS
    ৮
    0.68
    kenalkan
    0.67
    fts
    0.64
    व्ह
    0.64
    ৭
    0.63
    वंत
    0.61
    த்தில்
    0.60
    릭터
    0.60
    profit
    0.59
    رج
    0.59
    Activations Density 0.001%

    No Known Activations