© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246427
    Prev
    Next
    INDEX
    Explanations

    street, optimizers, grande, ver, piano, american, isle

    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
    ++];
    0.38
    Theta
    0.38
    hue
    0.38
    optera
    0.37
    Workers
    0.37
    Wax
    0.36
     Workers
    0.36
    investment
    0.36
     Wax
    0.36
    دیای
    0.36
    POSITIVE LOGITS
     अस्थायी
    0.42
    isp
    0.38
     қо
    0.37
     Temporary
    0.37
    盻
    0.37
     கொண்ட
    0.36
     mối
    0.36
    rootScope
    0.36
    scope
    0.35
     avsl
    0.35
    Activations Density 0.009%

    No Known Activations