© 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. 36521
    Prev
    Next
    INDEX
    Explanations

    soy milk

    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
    is
    0.98
    ي
    0.89
    as
    0.82
    et
    0.77
    다
    0.77
    ان
    0.76
    in
    0.75
    i
    0.74
    да
    0.73
     as
    0.73
    POSITIVE LOGITS
     écart
    0.71
    おそらく
    0.63
     priorité
    0.61
     cambi
    0.59
     mezcl
    0.59
     انرژی
    0.59
     ouvrage
    0.58
     arrondie
    0.58
     résist
    0.58
     creciendo
    0.57
    Activations Density 0.001%

    No Known Activations