© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131822
    Prev
    Next
    INDEX
    Explanations

    Fitzgerald

    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_6_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
    ي
    1.89
    י
    1.53
    ت
    1.29
    ك
    1.23
    ה
    1.22
    ，
    1.07
    ת
    1.06
    ם
    1.04
    ব
    1.01
    ства
    1.00
    POSITIVE LOGITS
    h
    1.34
    u
    1.07
     Ghent
    1.01
     Shenzhen
    1.00
     Tuscany
    0.98
     Munich
    0.97
    ar
    0.96
     ต
    0.95
     ngayon
    0.94
    im
    0.93
    Activations Density 0.000%

    No Known Activations