© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142193
    Prev
    Next
    INDEX
    Explanations

    rugs and mats

    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_12_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
     arctic
    0.52
    !
    0.51
     handic
    0.50
    ARE
    0.49
     ARE
    0.49
    iyorum
    0.49
     आरमारा
    0.49
     s
    0.49
     in
    0.49
     are
    0.49
    POSITIVE LOGITS
     когато
    0.52
    பிலோ
    0.51
     když
    0.49
    ან
    0.49
    (',');
    0.48
     когда
    0.47
     август
    0.46
     pajak
    0.46
    рел
    0.46
     agnostic
    0.46
    Activations Density 0.000%

    No Known Activations