© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150053
    Prev
    Next
    INDEX
    Explanations

    topped with crystal

    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_23_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
    ursday
    0.40
     waypoint
    0.37
     theme
    0.35
    메
    0.35
    api
    0.35
     Day
    0.35
     wages
    0.35
     powertrain
    0.34
     Talent
    0.34
    theme
    0.34
    POSITIVE LOGITS
    plaatst
    0.35
    πού
    0.34
     characterise
    0.34
    年来
    0.33
    ᔪ
    0.33
    อต
    0.33
    ISTICS
    0.32
    净化
    0.32
    椪
    0.32
    RESET
    0.32
    Activations Density 0.002%

    No Known Activations