© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115073
    Prev
    Next
    INDEX
    Explanations

    safe and helpful

    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_27_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
     vitally
    0.36
     contempl
    0.35
    쯜
    0.35
     жизнен
    0.34
     கீழ
    0.34
     tumb
    0.32
    Quanto
    0.32
     persec
    0.32
     hypoc
    0.32
    <unused68>
    0.32
    POSITIVE LOGITS
     नवरा
    0.35
     après
    0.34
    过后
    0.34
    Girl
    0.34
     picks
    0.33
     Picks
    0.32
     웹
    0.32
    blur
    0.31
     after
    0.31
    BtnUp
    0.31
    Activations Density 0.017%

    No Known Activations