© 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. 218909
    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
    ሎ
    0.41
     зада
    0.41
     azar
    0.41
    하지
    0.40
    荟
    0.39
    тай
    0.39
     मायणी
    0.38
    迷
    0.38
     ritorno
    0.37
    ORES
    0.37
    POSITIVE LOGITS
    estimates
    0.40
    CATEGORY
    0.39
    frontier
    0.38
     Estimates
    0.38
     estimated
    0.37
    plays
    0.37
    category
    0.36
    lean
    0.36
    infinity
    0.36
     मच्छर
    0.36
    Activations Density 0.000%

    No Known Activations