© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178269
    Prev
    Next
    INDEX
    Explanations

    group (

    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_29_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
    休息
    0.43
    rest
    0.37
     অংশে
    0.37
     >=
    0.36
    ishw
    0.36
    ﮯ
    0.35
    referrer
    0.34
    ിക്കും
    0.34
     paused
    0.34
     McCorm
    0.34
    POSITIVE LOGITS
     transnational
    0.42
     reacting
    0.38
     ત
    0.37
     transg
    0.37
     glLight
    0.36
     transgender
    0.36
     Haram
    0.36
     transatlantic
    0.36
     réactions
    0.36
     उसका
    0.35
    Activations Density 0.001%

    No Known Activations