© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29245
    Prev
    Next
    INDEX
    Explanations

    AUTO_INCREMENT

    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_40_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
    㧍
    0.40
    жами
    0.38
    öglichkeiten
    0.38
    persky
    0.38
    clinton
    0.37
    icios
    0.37
     eben
    0.37
    bred
    0.37
    oblast
    0.36
    SAV
    0.36
    POSITIVE LOGITS
     nucle
    0.38
    연
    0.37
     सहायता
    0.36
    വന
    0.36
    യ്യ
    0.36
    ค้น
    0.35
    负
    0.35
     rendez
    0.35
     Guillaume
    0.34
     භාවිත
    0.34
    Activations Density 0.000%

    No Known Activations