© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41839
    Prev
    Next
    INDEX
    Explanations

    Computing, explanation, non-English characters

    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_22_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
    南
    0.55
    ellä
    0.47
    藤
    0.46
    தெ
    0.46
     ainda
    0.44
    عي
    0.43
     jeszcze
    0.43
     beginnt
    0.43
    ز
    0.42
    Я
    0.42
    POSITIVE LOGITS
     :).
    0.50
     пирами
    0.49
    itipi
    0.46
     😁
    0.46
     डॉलर
    0.44
     枚
    0.44
    Occurrence
    0.44
     👍
    0.43
     Expenditure
    0.43
    帳に追加
    0.42
    Activations Density 0.000%

    No Known Activations