© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200065
    Prev
    Next
    INDEX
    Explanations

    name fragments

    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_50_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
    ች
    0.41
     APPROVED
    0.41
    knn
    0.39
    िं
    0.39
    кие
    0.38
    Kiza
    0.38
    ্যাগ
    0.38
    涫
    0.38
     caoutch
    0.38
     krzy
    0.38
    POSITIVE LOGITS
     Bran
    0.42
    Gl
    0.40
    Bu
    0.39
     Fold
    0.39
     Hal
    0.38
    butene
    0.38
     Ran
    0.38
     Ra
    0.37
    hal
    0.37
    MySQL
    0.37
    Activations Density 0.007%

    No Known Activations