© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170488
    Prev
    Next
    INDEX
    Explanations

    depict explicit

    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
     via
    0.33
     Process
    0.32
     Property
    0.32
    TimeString
    0.32
    认为
    0.31
    ]-
    0.31
     Database
    0.31
    （
    0.31
     Threshold
    0.31
    ৯৫
    0.31
    POSITIVE LOGITS
    ଯ
    0.38
    Ceylon
    0.37
     braids
    0.35
    ECK
    0.33
     preside
    0.33
     adequately
    0.33
     Brahm
    0.33
    CCIÓN
    0.33
     cooperated
    0.33
    Professor
    0.33
    Activations Density 0.018%

    No Known Activations