© 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. 175986
    Prev
    Next
    INDEX
    Explanations

    names like Khan

    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
    chromiumfx
    0.40
     lyn
    0.40
     phosph
    0.40
    Má
    0.40
    ÊN
    0.39
     flats
    0.39
    磷
    0.38
     conservación
    0.37
     Tug
    0.36
     sulf
    0.36
    POSITIVE LOGITS
    khan
    0.50
     Khan
    0.46
     ఖ
    0.44
     खान
    0.43
    pause
    0.41
    pal
    0.40
     Palmy
    0.40
     ഖ
    0.40
    Khan
    0.39
    anne
    0.38
    Activations Density 0.004%

    No Known Activations