© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139115
    Prev
    Next
    INDEX
    Explanations

    by mouth

    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_12_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
    ри
    0.47
    🤌
    0.43
    শিকান্ত
    0.43
     Ascot
    0.43
     game
    0.43
     legal
    0.42
     резко
    0.42
     Sargent
    0.42
     لع
    0.42
     Hukum
    0.42
    POSITIVE LOGITS
    INK
    0.55
    lips
    0.54
    P
    0.54
    %.
    0.52
    >*
    0.52
    tzmann
    0.52
    を作成
    0.52
    IIT
    0.52
    ock
    0.50
    kap
    0.50
    Activations Density 0.001%

    No Known Activations