© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64597
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Highlights
    0.38
    Occup
    0.37
     Occup
    0.36
    큘
    0.36
     occup
    0.36
    woff
    0.36
    Highlights
    0.36
    agliari
    0.35
     Highlight
    0.34
     OR
    0.34
    POSITIVE LOGITS
     fair
    0.46
    fair
    0.45
    lear
    0.42
    indeed
    0.42
     indeed
    0.42
     شوند
    0.42
    公平
    0.41
    嗣
    0.40
     forêt
    0.39
     справед
    0.38
    Activations Density 0.000%

    No Known Activations