© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2947
    Prev
    Next
    INDEX
    Explanations

    view context

    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_39_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
     දී
    0.40
    িয়েছেন
    0.39
     SHEET
    0.39
    शेखर
    0.38
     assuré
    0.38
    ൨
    0.38
    assured
    0.37
    staking
    0.36
     দিয়েছেন
    0.36
     کرکے
    0.35
    POSITIVE LOGITS
     Turqu
    0.38
     пом
    0.37
    тол
    0.37
     ž
    0.36
    ียบ
    0.35
     hä
    0.35
    Auf
    0.35
    ELTS
    0.35
    Trick
    0.35
    newBuilder
    0.35
    Activations Density 0.005%

    No Known Activations