© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167850
    Prev
    Next
    INDEX
    Explanations

    multiplication or division operators

    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_34_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
     Για
    0.41
     via
    0.39
     سنگ
    0.38
     interrupted
    0.38
    ιε
    0.37
    ulay
    0.37
     reap
    0.37
     勺
    0.37
    交易
    0.36
    Col
    0.36
    POSITIVE LOGITS
    foreground
    0.42
     முதல்
    0.41
    െല്ലാം
    0.40
     adequado
    0.39
    ಬ್ಬ
    0.39
    roductive
    0.38
    RIBUTION
    0.37
    лү
    0.37
     Soldaten
    0.37
    orene
    0.36
    Activations Density 0.002%

    No Known Activations