© 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. 129924
    Prev
    Next
    INDEX
    Explanations

    Command

    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
    -
    0.42
    asmim
    0.42
    ್ಯೂ
    0.39
     સ
    0.38
    axx
    0.38
    PAss
    0.38
     EP
    0.37
    assa
    0.37
    átky
    0.37
    0.35
    POSITIVE LOGITS
     Cav
    0.43
     \$
    0.41
    簫
    0.40
     $\$
    0.40
     zg
    0.40
     Ком
    0.39
     Zuck
    0.39
     bmp
    0.38
    zoni
    0.37
     xhr
    0.37
    Activations Density 0.002%

    No Known Activations