© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60534
    Prev
    Next
    INDEX
    Explanations

    optimize processes and resources

    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
     and
    0.67
     to
    0.63
    an
    0.61
     k
    0.61
    ur
    0.60
     s
    0.59
     of
    0.59
     with
    0.59
    v
    0.58
    ?
    0.58
    POSITIVE LOGITS
    ЕНИ
    0.62
     больш
    0.59
    تباه
    0.57
    ِلِّ
    0.56
     sammeln
    0.56
    koord
    0.55
    ᱖
    0.54
     فونیټ
    0.53
     کوئی
    0.53
    <0x8C>
    0.52
    Activations Density 0.006%

    No Known Activations