© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139971
    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_37_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
    Frost
    0.53
     Frost
    0.50
     इंजन
    0.41
    Frozen
    0.41
     congel
    0.39
     frost
    0.39
     Frozen
    0.38
    冻
    0.38
    frost
    0.38
     FRO
    0.36
    POSITIVE LOGITS
     museums
    0.41
     empir
    0.39
    duct
    0.39
    ovis
    0.38
     tribunals
    0.38
    बास
    0.38
    otus
    0.37
    博物馆
    0.37
    博物館
    0.37
    Declared
    0.36
    Activations Density 0.000%

    No Known Activations