© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29027
    Prev
    Next
    INDEX
    Explanations

    questions or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    j
    1.32
    و
    1.10
    h
    1.07
    ו
    1.03
    un
    1.02
    不
    1.02
    ق
    1.01
    ST
    0.94
    o
    0.90
    w
    0.90
    POSITIVE LOGITS
    ě
    0.87
    alaa
    0.85
     daños
    0.82
    いた
    0.82
     on
    0.78
    ים
    0.78
     próprios
    0.76
    एं
    0.75
    ating
    0.75
     एकमात्र
    0.75
    Activations Density 0.007%

    No Known Activations