© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53037
    Prev
    Next
    INDEX
    Explanations

    custom miniature, AI solutions, tailored dashboards

    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_31_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
    ロジー
    0.32
    监听
    0.31
     zár
    0.29
     miel
    0.29
     ად
    0.29
     जन्माष्टमी
    0.28
     ایڈ
    0.28
    細
    0.28
     kontrol
    0.27
     filozof
    0.27
    POSITIVE LOGITS
    чили
    0.32
     regulators
    0.29
     Statutes
    0.29
     coping
    0.28
     speculators
    0.28
     specialist
    0.27
     borrowers
    0.27
     индивидуа
    0.27
     correspondents
    0.27
    perger
    0.27
    Activations Density 0.006%

    No Known Activations