© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24217
    Prev
    Next
    INDEX
    Explanations

    near

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     closed
    2.53
     closes
    2.41
     закры
    2.41
     closing
    2.30
     Closed
    2.27
    Closed
    2.25
    闭
    2.23
     Closing
    2.17
    closed
    2.16
    Closing
    2.13
    POSITIVE LOGITS
     gord
    0.34
     proche
    0.34
    رحله
    0.34
    ≣
    0.34
    beq
    0.33
     नजदीक
    0.33
    íny
    0.33
    裴
    0.33
     समीप
    0.33
     propon
    0.32
    Activations Density 0.003%

    No Known Activations