© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 136959
    Prev
    Next
    INDEX
    Explanations

    all,todos,всеgo

    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
    oct
    0.57
    analyse
    0.56
    лы
    0.54
    url
    0.53
    apply
    0.53
    교
    0.52
    boiler
    0.52
    cal
    0.51
    че
    0.50
    inters
    0.50
    POSITIVE LOGITS
    ;
    0.68
    рт
    0.63
    )$.
    0.63
    к
    0.59
    ;')
    0.58
     Tiere
    0.57
    顷
    0.55
    .$;
    0.54
    °;
    0.53
    নার্থ
    0.52
    Activations Density 0.003%

    No Known Activations