© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7884
    Prev
    Next
    INDEX
    Explanations

    99.9% uptime

    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
    جے
    0.35
     মুজিবকে
    0.34
    ሒ
    0.32
     >=
    0.32
    ኽ
    0.32
     diffusion
    0.31
     mū
    0.31
    ጂ
    0.31
    rbrakk
    0.31
     כא
    0.30
    POSITIVE LOGITS
    Reli
    0.35
    Willow
    0.35
    ingly
    0.32
     पड़ोसी
    0.32
    reliable
    0.31
    urther
    0.31
     Willow
    0.31
     நம்ப
    0.30
     reliable
    0.30
    写真
    0.30
    Activations Density 0.002%

    No Known Activations