© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9956
    Prev
    Next
    INDEX
    Explanations

    never before or seen

    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_13_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
    K
    0.37
    ﺒ
    0.37
    би
    0.33
    Ov
    0.32
    𝘬
    0.32
    瑚
    0.31
    벡
    0.31
    نګ
    0.31
    ON
    0.30
    implies
    0.30
    POSITIVE LOGITS
    ív
    0.35
    艺
    0.31
     decked
    0.31
     впервые
    0.30
     Übersicht
    0.30
     mainu
    0.30
     outfitted
    0.30
    iyê
    0.29
     więc
    0.29
    ümer
    0.29
    Activations Density 0.056%

    No Known Activations