© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206325
    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
    skiy
    0.44
    reda
    0.42
     સ્ક
    0.41
    थे
    0.40
     fu
    0.39
     fong
    0.37
    ඖ
    0.37
    贄
    0.37
    raul
    0.36
    樓
    0.35
    POSITIVE LOGITS
    Yesterday
    0.37
    ση
    0.37
     Holes
    0.36
    يط
    0.36
    зон
    0.35
    ნიშვნელ
    0.35
     önemlidir
    0.35
    緘
    0.35
    $"
    0.34
     Yesterday
    0.34
    Activations Density 0.000%

    No Known Activations