© 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. 76862
    Prev
    Next
    INDEX
    Explanations

    drawing curves with bezier or quadratic

    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_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
    𝘈
    0.43
     sabor
    0.41
     ivvu
    0.41
    ⌛
    0.41
     relem
    0.40
    uerpo
    0.40
     redis
    0.38
    祺
    0.38
    
    0.38
    ⏪
    0.38
    POSITIVE LOGITS
    Zig
    0.48
    zigzag
    0.45
    Contact
    0.43
    Chapter
    0.43
     zig
    0.41
    Literal
    0.38
     Contacts
    0.38
     zigzag
    0.37
    Conflict
    0.35
    Resistance
    0.35
    Activations Density 0.003%

    No Known Activations