© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11881
    Prev
    Next
    INDEX
    Explanations

    fill color

    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_40_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
     shades
    0.47
     紫
    0.46
     nuances
    0.40
     labelled
    0.40
     labeled
    0.37
    labelled
    0.37
    bmp
    0.35
     Shades
    0.35
     magenta
    0.35
    coloured
    0.35
    POSITIVE LOGITS
    Crow
    0.38
     Hi
    0.38
    Hi
    0.38
    臼
    0.38
    默认
    0.36
     alimentaires
    0.35
    Module
    0.35
    MathClass
    0.34
     Lulu
    0.34
    Sunny
    0.34
    Activations Density 0.003%

    No Known Activations