© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245984
    Prev
    Next
    INDEX
    Explanations

    dice, building, craps, catan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    เมนต์
    0.42
    Lay
    0.41
    กล้
    0.40
    System
    0.40
    Ethnic
    0.39
    ·
    0.39
    Council
    0.38
    Systems
    0.38
    Format
    0.37
    Guard
    0.37
    POSITIVE LOGITS
     PTR
    0.44
     finance
    0.41
    wikimedia
    0.41
     длин
    0.40
     finances
    0.39
     桌
    0.39
    datos
    0.39
    ്ര
    0.38
     долго
    0.38
     ಪಿ
    0.38
    Activations Density 0.001%

    No Known Activations