© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139175
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     P
    0.63
    J
    0.46
    P
    0.46
     J
    0.44
     Prit
    0.44
     ஜ
    0.43
    פרי
    0.39
     QA
    0.37
     JA
    0.37
    Biz
    0.37
    POSITIVE LOGITS
    gub
    0.42
    gled
    0.39
     Dubey
    0.39
    ಡುವುದ
    0.38
    axies
    0.38
     Gip
    0.38
    <0x93>
    0.38
    arrerol
    0.38
     محض
    0.38
    <0xA0>
    0.37
    Activations Density 0.027%

    No Known Activations