© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103744
    Prev
    Next
    INDEX
    Explanations

    ions

    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_1_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
    ;
    0.97
    ية
    0.96
     claras
    0.96
    них
    0.95
     важ
    0.93
     sozial
    0.91
     která
    0.89
     suffisante
    0.88
     факти
    0.88
    oration
    0.87
    POSITIVE LOGITS
    ان
    1.11
     It
    1.03
    다
    1.03
    t
    0.99
    an
    0.97
    א
    0.95
    à
    0.95
    ก
    0.94
    sw
    0.94
    ח
    0.94
    Activations Density 0.001%

    No Known Activations