© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31453
    Prev
    Next
    INDEX
    Explanations

    Matthew, arguments, window coordinates, kernel operations

    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_31_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
     uncond
    0.44
    ຼ
    0.38
     Moist
    0.37
    APOLIS
    0.37
    ര്‍ട്ട്
    0.37
     neder
    0.36
     unbear
    0.36
    echen
    0.35
     नमी
    0.35
    闷
    0.35
    POSITIVE LOGITS
     ถ
    0.39
     înv
    0.38
     tray
    0.37
    Beta
    0.37
    trash
    0.37
     산
    0.36
    label
    0.36
     PAT
    0.35
     योग
    0.35
     syg
    0.35
    Activations Density 0.046%

    No Known Activations