© 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. 204186
    Prev
    Next
    INDEX
    Explanations

    leaves

    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
     leaves
    2.58
     Leaves
    2.36
    Leaves
    2.31
    leaves
    2.25
     листь
    1.73
    葉
    1.73
     foglie
    1.71
     листья
    1.68
     feuilles
    1.60
    叶
    1.59
    POSITIVE LOGITS
     dab
    0.36
     遊
    0.36
    હે
    0.36
     spur
    0.36
     rack
    0.35
    .)
    0.35
    optic
    0.34
    遊
    0.34
     dri
    0.34
     db
    0.34
    Activations Density 0.003%

    No Known Activations