© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57379
    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_59_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
     باپ
    0.45
    ा
    0.45
    batt
    0.40
    ়া
    0.40
    neh
    0.38
    া
    0.37
    idin
    0.36
    pq
    0.36
     बत्रा
    0.36
    bim
    0.36
    POSITIVE LOGITS
    ган
    0.46
    kur
    0.44
    gano
    0.43
    ਗਾ
    0.41
    гово
    0.40
    ্কর
    0.40
    熬
    0.40
    トリック
    0.39
    gments
    0.39
    кур
    0.39
    Activations Density 0.000%

    No Known Activations