© 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. 31674
    Prev
    Next
    INDEX
    Explanations

    pygame

    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
     আসিয়া
    0.35
     مہ
    0.34
    Дата
    0.33
    蓼
    0.33
     زین
    0.32
    oarthritis
    0.32
     প্রার্থ
    0.32
    ;');
    0.32
     দিয়া
    0.32
    ');//
    0.31
    POSITIVE LOGITS
    ``
    0.39
     ref
    0.35
     -
    0.33
    Row
    0.30
    rl
    0.29
    ften
    0.29
     Row
    0.29
    pl
    0.29
    clu
    0.29
    hea
    0.28
    Activations Density 0.001%

    No Known Activations