© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213930
    Prev
    Next
    INDEX
    Explanations

    Thanks

    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_47_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
    里昂
    0.42
     probed
    0.41
     многое
    0.41
     保
    0.41
    coons
    0.40
    También
    0.39
    കൻ
    0.39
     будем
    0.39
    格兰
    0.39
     провод
    0.39
    POSITIVE LOGITS
     Z
    0.42
     relatively
    0.40
    ners
    0.39
    রির
    0.39
     Meal
    0.37
    OGLE
    0.37
    Z
    0.36
     real
    0.35
    avirus
    0.35
    NERS
    0.35
    Activations Density 0.000%

    No Known Activations