© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18447
    Prev
    Next
    INDEX
    Explanations

    margin-

    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_40_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
    項
    0.40
     neder
    0.38
     項
    0.38
    項目
    0.38
    퐈
    0.37
     lique
    0.37
     jammed
    0.36
     품
    0.36
    hém
    0.36
     jamming
    0.36
    POSITIVE LOGITS
     Based
    0.38
    spath
    0.36
     Choices
    0.36
     ~=
    0.35
     Couldn
    0.35
    Blu
    0.35
     PS
    0.35
     based
    0.34
     Paisley
    0.34
     ад
    0.34
    Activations Density 0.002%

    No Known Activations