© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65756
    Prev
    Next
    INDEX
    Explanations

    field types: Select, Boolean, Bytes, None

    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_41_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
    [[
    0.42
    🔪
    0.41
     कराते
    0.41
    jasper
    0.40
    wilderness
    0.39
     पड़ी
    0.39
    Mountain
    0.38
    [%
    0.38
     बैन
    0.38
    [["
    0.38
    POSITIVE LOGITS
     BSC
    0.82
     Sed
    0.73
     Type
    0.67
     SED
    0.67
    Type
    0.66
     sed
    0.62
     sedation
    0.58
     social
    0.57
     Social
    0.56
    Sed
    0.54
    Activations Density 0.115%

    No Known Activations