© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154503
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     PAN
    0.39
     শতকরা
    0.39
     JAN
    0.38
    we
    0.38
    vore
    0.38
    vase
    0.37
    钺
    0.37
     män
    0.36
     maka
    0.36
     når
    0.36
    POSITIVE LOGITS
    теря
    0.43
    負責
    0.43
    INTEGER
    0.40
    聲音
    0.39
    ონის
    0.39
    自身の
    0.39
     график
    0.39
    тери
    0.38
    退
    0.38
    عمل
    0.38
    Activations Density 0.000%

    No Known Activations