© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198000
    Prev
    Next
    INDEX
    Explanations

    MS ) or ME )

    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_4_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
    it
    1.90
    é
    1.32
    al
    1.29
    ak
    1.27
    ai
    1.27
    em
    1.25
    ing
    1.20
    os
    1.16
    od
    1.15
    ate
    1.14
    POSITIVE LOGITS
    く
    1.04
    す
    0.98
    ク
    0.98
    ٦
    0.98
    inį
    0.96
    ８
    0.93
    ﾙ
    0.92
    ъл
    0.91
    ۶
    0.91
    มอ
    0.90
    Activations Density 0.001%

    No Known Activations