© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61031
    Prev
    Next
    INDEX
    Explanations

    zero to something

    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_11_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
    ザー
    0.63
    ный
    0.63
    ის
    0.61
    ">(</
    0.61
    Name
    0.60
     Мне
    0.60
    ේ
    0.58
    ле
    0.57
    вания
    0.57
    F
    0.57
    POSITIVE LOGITS
    o
    0.85
    ו
    0.72
     bodyguard
    0.67
     demographic
    0.65
    ร
    0.63
     coval
    0.63
     到
    0.62
     bened
    0.61
    ang
    0.61
    n
    0.61
    Activations Density 0.002%

    No Known Activations