© 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. 48168
    Prev
    Next
    INDEX
    Explanations

    pagination and limiting

    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
    rotation
    0.29
    poem
    0.27
    세대
    0.27
    stab
    0.27
     ሰ
    0.27
    wohl
    0.27
    簡單
    0.27
    methoxy
    0.26
    ારીખ
    0.26
    storage
    0.26
    POSITIVE LOGITS
    Ἥ
    0.29
     Sorting
    0.28
     côn
    0.28
     palestra
    0.28
     Cyp
    0.27
     sorting
    0.27
     ממש
    0.27
     Cyprus
    0.27
    loggedIn
    0.26
     잘못
    0.26
    Activations Density 0.002%

    No Known Activations