© 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. 77358
    Prev
    Next
    INDEX
    Explanations

    file paths and security contexts

    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
    價
    0.34
     compagnia
    0.33
     eateries
    0.33
     compañeros
    0.31
    埆
    0.31
     சாப்பி
    0.30
    兕
    0.30
    很快
    0.30
    Sir
    0.29
     compañías
    0.29
    POSITIVE LOGITS
    zig
    0.32
     Duplicate
    0.31
     duplicate
    0.30
     posiada
    0.29
     specifically
    0.29
     zig
    0.29
     insignificant
    0.28
     insign
    0.28
     Zig
    0.27
     znám
    0.27
    Activations Density 0.000%

    No Known Activations