© 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. 170523
    Prev
    Next
    INDEX
    Explanations

    meat and animal protein sources

    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
     unfore
    0.49
    ニング
    0.48
     acog
    0.46
     prejudices
    0.44
     forbidding
    0.44
    ｍｍ
    0.43
     civilized
    0.43
    僥
    0.43
    annels
    0.42
    イール
    0.41
    POSITIVE LOGITS
     Tech
    0.47
    Tech
    0.46
    Cap
    0.45
    點
    0.44
    LIN
    0.43
    LE
    0.42
     Teacher
    0.42
    Teacher
    0.42
    Report
    0.42
    TECH
    0.42
    Activations Density 0.001%

    No Known Activations