© 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. 9039
    Prev
    Next
    INDEX
    Explanations

    the most best

    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
    game
    0.37
    int
    0.33
    for
    0.32
    Out
    0.31
    c
    0.31
     for
    0.31
     For
    0.31
    ally
    0.31
    ford
    0.31
    robot
    0.30
    POSITIVE LOGITS
     chrysanthemum
    0.39
     میکرز
    0.37
    ဏ
    0.37
     cleats
    0.36
     stiffness
    0.36
     stiff
    0.35
     stiffer
    0.35
    ଷ
    0.35
     clothe
    0.35
     buds
    0.34
    Activations Density 0.025%

    No Known Activations