© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2465
    Prev
    Next
    INDEX
    Explanations

    html closing tags

    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
    殊
    0.39
     SOLD
    0.38
    SOLD
    0.38
     Prote
    0.38
     Sold
    0.37
     getContentPane
    0.36
     Vitt
    0.36
     отдельно
    0.36
    ピオン
    0.36
    내는
    0.35
    POSITIVE LOGITS
    alpha
    0.43
    style
    0.43
    Osc
    0.41
    div
    0.40
    a
    0.40
    CC
    0.39
    styles
    0.39
    initial
    0.39
    zen
    0.38
    Pais
    0.38
    Activations Density 0.020%

    No Known Activations