© 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. 31813
    Prev
    Next
    INDEX
    Explanations

    say "clear"

    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
     Sa
    0.41
    stehen
    0.41
     râ
    0.39
    Parse
    0.38
    Sa
    0.38
    ambe
    0.38
    VG
    0.37
    ڎ
    0.37
    Baba
    0.37
    اکر
    0.36
    POSITIVE LOGITS
     klar
    0.97
     Clear
    0.81
    klar
    0.77
     claros
    0.77
     klare
    0.76
     claras
    0.75
     clear
    0.74
     Claro
    0.73
    Clear
    0.71
     Klar
    0.71
    Activations Density 0.021%

    No Known Activations