© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133005
    Prev
    Next
    INDEX
    Explanations

    geometric figure

    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_6_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
    :
    1.34
    ;
    0.97
    ↵↵
    0.97
    '
    0.96
     (
    0.94
    am
    0.87
     ни
    0.87
    ak
    0.80
    ן
    0.78
     husky
    0.77
    POSITIVE LOGITS
    h
    1.29
    t
    1.27
    v
    1.13
    ت
    1.08
    í
    1.04
    ü
    0.99
    linhas
    0.91
    u
    0.88
    sen
    0.88
    service
    0.88
    Activations Density 0.001%

    No Known Activations