© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165366
    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_31_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
    untu
    0.40
    ussion
    0.39
    entered
    0.39
     Grade
    0.39
     удержи
    0.38
    凭
    0.38
     Trag
    0.38
    ']])
    0.38
    ouchers
    0.38
     SELECT
    0.37
    POSITIVE LOGITS
     casein
    0.42
    ப்படுத்து
    0.41
    案
    0.41
     emigration
    0.39
     casework
    0.38
     cook
    0.37
     migration
    0.37
     coron
    0.37
     다
    0.37
     coverage
    0.36
    Activations Density 0.000%

    No Known Activations