© 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. 80783
    Prev
    Next
    INDEX
    Explanations

    business and place names

    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
     inextricably
    0.36
     Владимира
    0.35
     chairmanship
    0.35
     specifying
    0.34
     eines
    0.34
    arganya
    0.34
     Leibniz
    0.34
     ณ
    0.33
     telling
    0.33
     calmly
    0.33
    POSITIVE LOGITS
     Income
    0.40
    荤
    0.38
    Fridge
    0.36
    ovce
    0.35
     income
    0.34
    Delta
    0.33
    Temperature
    0.33
    VISED
    0.33
    sight
    0.33
     Temperature
    0.33
    Activations Density 0.004%

    No Known Activations