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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144989
    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_0_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
    ซ
    0.62
    ন
    0.60
    ب
    0.57
     interno
    0.56
     gigs
    0.56
    ك
    0.56
    ก
    0.56
    ي
    0.55
     obstructive
    0.54
    天氣
    0.54
    POSITIVE LOGITS
    Methoxy
    0.60
    lipid
    0.57
    portion
    0.55
    exceptions
    0.53
    molecular
    0.53
    marginal
    0.53
    kinetic
    0.53
    quadratic
    0.53
    ↵
    0.52
    ntgen
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.