© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12365
    Prev
    Next
    INDEX
    Explanations

    javascript, cpp, and code snippets

    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_40_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
    Accommodation
    0.46
     Accommodation
    0.44
    เปลี่ยนแปลง
    0.41
    𝑯
    0.40
    Separ
    0.39
    Translator
    0.39
    แยก
    0.38
    分离
    0.37
     আসিয়
    0.37
    拡
    0.37
    POSITIVE LOGITS
     manis
    0.42
     game
    0.41
     gef
    0.41
     Morris
    0.40
     कठ
    0.40
    ગ્ર
    0.40
    マン
    0.40
     eksp
    0.38
     meisjes
    0.38
     eich
    0.38
    Activations Density 0.001%

    No Known Activations