© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82217
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    Muh
    0.40
     Muh
    0.37
    ที่สุด
    0.36
    สุด
    0.36
     ({\
    0.36
    рость
    0.36
    íveis
    0.35
    ตก
    0.35
    jin
    0.34
    нак
    0.34
    POSITIVE LOGITS
     আঘাতে
    0.41
    鲶
    0.40
    讵
    0.40
    uation
    0.40
     Way
    0.40
    '`
    0.40
     আসলেই
    0.39
     Heath
    0.38
    不止
    0.38
    Washington
    0.37
    Activations Density 0.000%

    No Known Activations