© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39619
    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_57_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
     Jewish
    0.42
    회의
    0.37
    的关键
    0.37
     Salvador
    0.37
    佤
    0.37
     proved
    0.36
     plod
    0.36
    slug
    0.35
    Inspector
    0.35
     freeze
    0.34
    POSITIVE LOGITS
     denominations
    0.40
    ബ്ര
    0.36
    umination
    0.35
     室
    0.34
     جاسک
    0.34
     diseñ
    0.34
     denomin
    0.34
     طراحی
    0.34
     ગયા
    0.34
    asan
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.