© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80408
    Prev
    Next
    INDEX
    Explanations

    Men followed by os, or, jar

    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_0_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
    ir
    2.22
    e
    2.02
    p
    2.02
    in
    1.85
    y
    1.81
     an
    1.80
     in
    1.78
    X
    1.77
    ing
    1.75
     In
    1.69
    POSITIVE LOGITS
    ዴት
    1.20
    لیکن
    1.17
    тую
    1.15
    ją
    1.14
    туга
    1.14
    ról
    1.13
    ités
    1.11
    barui
    1.10
    τή
    1.09
    سک
    1.09
    Activations Density 0.001%

    No Known Activations