© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237147
    Prev
    Next
    INDEX
    Explanations

    ASCII art eyes

    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_32_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
     caffè
    0.34
     declines
    0.34
    cafe
    0.33
    ประชุม
    0.33
    idur
    0.33
    𒅆
    0.33
     clothes
    0.32
     Dance
    0.32
     fluct
    0.32
     plummeted
    0.32
    POSITIVE LOGITS
    Ensure
    0.34
    ➸
    0.32
     ഭരണ
    0.32
     unincorporated
    0.32
    ੨
    0.32
    <unused30>
    0.32
    Richard
    0.31
    答应
    0.31
    აბ
    0.31
    Tom
    0.31
    Activations Density 0.002%

    No Known Activations