© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3636
    Prev
    Next
    INDEX
    Explanations

    `defun`, `defpackage`, `defvar`

    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_40_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
     karo
    0.43
    삵
    0.40
    izo
    0.39
     dissolve
    0.39
     otr
    0.39
    slice
    0.38
    caption
    0.38
    িতার
    0.38
     charms
    0.37
    cture
    0.37
    POSITIVE LOGITS
    ::::::
    0.38
     سلسله
    0.38
     ENGINEER
    0.38
    ELI
    0.37
    번
    0.37
    发生
    0.36
     LZ
    0.36
     L
    0.36
     LDH
    0.36
    ура
    0.36
    Activations Density 0.002%

    No Known Activations