© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79425
    Prev
    Next
    INDEX
    Explanations

    DIVISION

    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
    al
    1.89
    จะ
    1.52
    -
    1.47
    ing
    1.44
    as
    1.41
    या
    1.38
    n
    1.34
    /
    1.25
    न
    1.25
    is
    1.24
    POSITIVE LOGITS
    ের
    1.66
    ુ
    1.66
    ים
    1.55
    ओं
    1.45
    ０
    1.41
     in
    1.35
    ો
    1.35
     be
    1.32
    0
    1.32
    もら
    1.30
    Activations Density 0.000%

    No Known Activations