© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172456
    Prev
    Next
    INDEX
    Explanations

    figures and tables

    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_20_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
     quantitative
    0.23
    ftÂ
    0.23
    沛
    0.23
    upper
    0.22
    wv
    0.22
    年底
    0.22
     managerial
    0.22
    ↵↵↵↵↵↵↵
    0.22
     UFO
    0.22
    학년
    0.22
    POSITIVE LOGITS
     disassemble
    0.26
     unatt
    0.25
     afresh
    0.25
    Ginger
    0.25
     dismant
    0.24
     Loksatta
    0.24
     mì
    0.23
    िडिओ
    0.23
    ज़
    0.23
     Hiro
    0.23
    Activations Density 0.000%

    No Known Activations