© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 213574
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ボル
    0.40
    binary
    0.38
     dương
    0.36
     DP
    0.35
     ኣ
    0.35
     dap
    0.35
    kbeta
    0.35
    广东
    0.35
     Indonesian
    0.34
    ાડ
    0.34
    POSITIVE LOGITS
    lel
    0.43
    Finish
    0.41
    ಃ
    0.40
     моего
    0.39
     Gogh
    0.38
     Antim
    0.38
     وج
    0.37
    に行った
    0.37
    Tie
    0.37
     Ultim
    0.37
    Activations Density 0.000%

    No Known Activations