© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193967
    Prev
    Next
    INDEX
    Explanations

    rephrase, Taycan, Piper picked

    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_15_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
    ן
    0.52
     ד
    0.51
     habil
    0.51
     vaccin
    0.48
    ค
    0.47
    -
    0.47
     ص
    0.45
     escrib
    0.44
     ס
    0.44
     square
    0.44
    POSITIVE LOGITS
    Flowers
    0.48
    getCharAt
    0.48
    êmes
    0.47
    ड़ियां
    0.46
    कोप
    0.46
     Spirits
    0.46
    ullivan
    0.46
    éries
    0.45
    Watt
    0.45
    nikom
    0.45
    Activations Density 0.001%

    No Known Activations