© 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. 31564
    Prev
    Next
    INDEX
    Explanations

    python

    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
    ッピング
    0.50
    psz
    0.44
    rho
    0.43
    Cpp
    0.43
    Ｐ
    0.43
    Lua
    0.43
     pł
    0.43
    Ṕ
    0.42
    psi
    0.41
    Rho
    0.41
    POSITIVE LOGITS
    また
    0.39
    autista
    0.38
     Gute
    0.36
    idan
    0.36
    dN
    0.35
    B
    0.35
    ódromo
    0.35
     Marcy
    0.35
    ȧ
    0.35
    آ
    0.34
    Activations Density 0.022%

    No Known Activations