© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208007
    Prev
    Next
    INDEX
    Explanations

    go ahead

    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_10_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
    ீக
    0.70
     лише
    0.68
    ви
    0.63
    эй
    0.61
    ਾ
    0.61
    कृत
    0.60
     additions
    0.60
     форме
    0.59
    ージェ
    0.58
    quisites
    0.58
    POSITIVE LOGITS
    UM
    0.84
    IL
    0.80
    inch
    0.77
    of
    0.74
     tahun
    0.73
    Us
    0.71
     način
    0.71
    ۔
    0.69
    IF
    0.69
    IR
    0.68
    Activations Density 0.000%

    No Known Activations