© 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. 231543
    Prev
    Next
    INDEX
    Explanations

    backwards

    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
    Ü
    1.25
    N
    0.97
    İ
    0.97
    d
    0.96
    ER
    0.96
    Ä
    0.96
    Đ
    0.92
     has
    0.91
    z
    0.90
    אל
    0.89
    POSITIVE LOGITS
    ur
    1.55
    ни
    1.29
    ist
    1.22
    ну
    1.20
    не
    1.16
    in
    1.14
    ди
    1.13
    il
    1.11
    у
    1.11
    த்
    1.08
    Activations Density 0.000%

    No Known Activations