© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23411
    Prev
    Next
    INDEX
    Explanations

    ins and outs

    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_56_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
     Unwrap
    0.34
    働き
    0.34
    시키
    0.33
     Coefficients
    0.33
    篇
    0.33
    capi
    0.32
    申し上げ
    0.32
     lumi
    0.32
     headless
    0.31
    蓆
    0.31
    POSITIVE LOGITS
     ins
    2.05
     Ins
    1.78
    Ins
    1.69
     outs
    1.61
     Outs
    1.52
    ins
    1.48
     ups
    1.45
     overs
    1.30
    outs
    1.23
     INS
    1.20
    Activations Density 0.034%

    No Known Activations