© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166995
    Prev
    Next
    INDEX
    Explanations

    viewport width="device-width" initial-scale="1.0"

    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_31_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
    誰
    0.33
     dissemination
    0.31
     無
    0.30
    涟
    0.30
    هره
    0.29
    rala
    0.29
    麸
    0.29
    enzyme
    0.29
    গম
    0.29
    螂
    0.29
    POSITIVE LOGITS
     Cus
    0.38
     cus
    0.38
     opposit
    0.33
    陈
    0.31
    ピッ
    0.31
    织
    0.31
     kus
    0.30
     Romantic
    0.30
    ąpi
    0.30
    ോ
    0.29
    Activations Density 0.001%

    No Known Activations