© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46485
    Prev
    Next
    INDEX
    Explanations

    Vitamin A

    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_22_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
     totalSupply
    0.46
     Overseas
    0.44
    cemic
    0.44
    例文帳に追加
    0.43
    ㎏
    0.42
    ^{\
    0.41
     प्रोफ
    0.41
     किलोग्राम
    0.40
     OTP
    0.40
     Leung
    0.40
    POSITIVE LOGITS
     ;)
    0.46
    :)
    0.45
    ገኛ
    0.45
     barking
    0.45
    networking
    0.44
     :).
    0.44
     :)
    0.42
    Networking
    0.42
     vaše
    0.41
     grids
    0.41
    Activations Density 0.002%

    No Known Activations