© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145070
    Prev
    Next
    INDEX
    Explanations

    reparations

    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_0_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
     Дж
    1.24
     $
    1.19
     お知らせ
    1.19
     ﺍ
    1.18
     Α
    1.16
     Г
    1.13
    あり
    1.13
     Ком
    1.13
     К
    1.11
     И
    1.11
    POSITIVE LOGITS
    ك
    2.00
    و
    1.85
    ش
    1.70
    de
    1.67
    2
    1.65
    व
    1.59
    ur
    1.54
    ية
    1.53
    로
    1.52
    ен
    1.52
    Activations Density 0.000%

    No Known Activations