© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34528
    Prev
    Next
    INDEX
    Explanations

    to their / completely back

    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_7_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
     to
    1.24
     of
    1.02
    to
    0.96
     be
    0.95
    ä
    0.93
     that
    0.79
     r
    0.77
    de
    0.73
     from
    0.70
     र
    0.70
    POSITIVE LOGITS
    ↵
    0.95
    kken
    0.82
    k
    0.80
    ಗಾಗಿ
    0.74
    ká
    0.69
    ６
    0.69
    ம்
    0.68
    ký
    0.68
    其他
    0.66
    聪明
    0.65
    Activations Density 0.095%

    No Known Activations