© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36814
    Prev
    Next
    INDEX
    Explanations

    perplexity and confusion

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     આવ
    0.39
     الر
    0.38
     ep
    0.37
     ఎదు
    0.36
    檔
    0.36
    ంతరం
    0.36
     workflow
    0.35
     prioritized
    0.34
    疫
    0.34
     Cool
    0.34
    POSITIVE LOGITS
    jx
    0.40
    aset
    0.39
    Lauren
    0.38
    mitz
    0.38
    jm
    0.37
    steelblue
    0.36
    ¦
    0.36
    ,_
    0.36
    रम
    0.36
    Canadian
    0.35
    Activations Density 0.000%

    No Known Activations