© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176367
    Prev
    Next
    INDEX
    Explanations

    BERTopic

    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_20_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
    riculum
    0.48
     শিক্ষা
    0.47
     ప్రపంచ
    0.45
     शिक्षा
    0.44
     Ҳ
    0.44
    mination
    0.44
     ശിഷ്യ
    0.43
     फीफा
    0.42
    শুধ
    0.42
     वर्ल्ड
    0.42
    POSITIVE LOGITS
     pendant
    0.38
    [*
    0.37
     array
    0.36
    反
    0.36
     stock
    0.36
     occurrences
    0.36
    店の
    0.36
     retrouver
    0.36
     displaying
    0.35
    ोटी
    0.35
    Activations Density 0.000%

    No Known Activations