© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221308
    Prev
    Next
    INDEX
    Explanations

    @Transactional

    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_10_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
    0.78
    ي
    0.71
    可以
    0.62
     Squares
    0.55
     Honeywell
    0.55
     Cassandra
    0.54
    т
    0.54
     Standards
    0.52
     lask
    0.52
    ið
    0.52
    POSITIVE LOGITS
     войск
    0.63
    ্যেষ্ঠ
    0.53
    enhance
    0.53
    intérêt
    0.52
    accueil
    0.52
    isku
    0.51
     ভাষা
    0.50
    sinh
    0.50
    𝗴
    0.50
    begin
    0.50
    Activations Density 0.000%

    No Known Activations