© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91340
    Prev
    Next
    INDEX
    Explanations

    Samurai, Japan, Ira, Cooke, Samaria

    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_3_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
    จะ
    0.96
    고
    0.84
    ل
    0.83
    ر
    0.79
    ت
    0.75
    由
    0.72
    是
    0.70
    市
    0.70
    在于
    0.70
    ない
    0.70
    POSITIVE LOGITS
     is
    0.71
    IC
    0.70
    0.64
    ln
    0.63
     for
    0.62
    uj
    0.62
     or
    0.61
    IT
    0.61
    ml
    0.61
     I
    0.59
    Activations Density 0.000%

    No Known Activations