© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231332
    Prev
    Next
    INDEX
    Explanations

    Mediterranean, cleansing, Kane, Sumatra

    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_6_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
    i
    1.61
    ac
    0.93
    1
    0.93
    glomer
    0.89
    ið
    0.88
    י
    0.88
    ي
    0.88
    iin
    0.86
    .".
    0.86
    AR
    0.84
    POSITIVE LOGITS
     has
    1.28
    л
    1.27
    ב
    1.20
    า
    1.19
    я
    1.09
     to
    1.07
    ก
    1.05
    ক
    0.98
     on
    0.95
    ма
    0.94
    Activations Density 0.000%

    No Known Activations