© 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. 132671
    Prev
    Next
    INDEX
    Explanations

    freshly cracked pepper

    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
    कां
    0.43
     Mystery
    0.43
    $&$-
    0.42
    ᑖ
    0.40
    PELL
    0.40
    Mystery
    0.39
    .&
    0.38
    worm
    0.37
    ट्टे
    0.37
    oski
    0.37
    POSITIVE LOGITS
     вироб
    0.37
    egaard
    0.37
     lớ
    0.36
    >.</
    0.35
     장
    0.35
     ')[
    0.35
     olursa
    0.34
    arded
    0.34
     zorg
    0.33
    ня
    0.33
    Activations Density 0.002%

    No Known Activations