© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57972
    Prev
    Next
    INDEX
    Explanations

    separation tokens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     RULES
    0.40
     rules
    0.36
    cology
    0.35
     benchmarks
    0.35
     hinges
    0.34
    朼
    0.33
    नाने
    0.33
    UMBIA
    0.33
    ليو
    0.33
    automne
    0.33
    POSITIVE LOGITS
     and
    0.56
     Area
    0.54
    /,
    0.46
     Region
    0.46
     및
    0.45
     ,\
    0.45
     Face
    0.44
     ，
    0.44
    (),
    0.43
     மற்றும்
    0.41
    Activations Density 0.003%

    No Known Activations