© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87154
    Prev
    Next
    INDEX
    Explanations

    variety of

    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
    ag
    1.00
    ak
    0.80
    it
    0.72
    ahin
    0.68
    ing
    0.66
    of
    0.65
    ه
    0.63
    urezza
    0.63
    a
    0.63
    yl
    0.62
    POSITIVE LOGITS
    צ
    0.82
    ў
    0.74
    ז
    0.73
    ל
    0.68
    ません
    0.68
    ן
    0.67
    ц
    0.63
    ปี
    0.62
    ά
    0.62
    する
    0.61
    Activations Density 0.000%

    No Known Activations