© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176317
    Prev
    Next
    INDEX
    Explanations

    event details

    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_50_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
     মুখো
    0.43
    ✙
    0.41
    رش
    0.38
    ارس
    0.38
    槍
    0.38
    bert
    0.38
    opically
    0.37
    ₚ
    0.37
    geoLocation
    0.37
    ored
    0.37
    POSITIVE LOGITS
    ಣ್ಣ
    0.41
    FEN
    0.40
     канали
    0.39
    Cap
    0.38
    No
    0.38
    Castle
    0.38
     Transitions
    0.38
     剤
    0.38
     Анали
    0.37
    뜬
    0.37
    Activations Density 0.000%

    No Known Activations