© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45147
    Prev
    Next
    INDEX
    Explanations

    gyatso, gyarados, gyula, gyuto

    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
     μορ
    0.67
     osobow
    0.64
     carbure
    0.62
     λι
    0.62
    を入れて
    0.61
     взя
    0.60
     rodzin
    0.60
    ي
    0.60
     বাসায়
    0.59
     δή
    0.59
    POSITIVE LOGITS
    da
    0.86
    d
    0.82
    b
    0.80
    ם
    0.73
    dan
    0.72
    EL
    0.72
    sp
    0.70
    場合
    0.70
    df
    0.70
    ON
    0.68
    Activations Density 0.000%

    No Known Activations