© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26720
    Prev
    Next
    INDEX
    Explanations

    Bellwether, Bellic, Belucci

    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_10_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
    o
    0.83
    t
    0.82
    -
    0.82
    ’:
    0.75
    देख
    0.73
    ’-
    0.73
    -]+
    0.71
    ر
    0.70
    ar
    0.69
    According
    0.69
    POSITIVE LOGITS
     εκ
    0.70
     الك
    0.69
     ಗೌ
    0.67
    6
    0.67
     rigu
    0.67
     μα
    0.66
    იან
    0.66
    olic
    0.65
    たす
    0.65
     πολ
    0.63
    Activations Density 0.000%

    No Known Activations