© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    visual novel, character archetypes, Garry's Mod

    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
    า
    0.56
    f
    0.53
    انگ
    0.46
    el
    0.44
    д
    0.43
    ล
    0.43
     OF
    0.42
    ن
    0.42
    ה
    0.42
     F
    0.42
    POSITIVE LOGITS
    的发展
    0.47
    BackgroundColor
    0.45
    Cookie
    0.45
     czasu
    0.42
    Witam
    0.42
    ği
    0.41
    Juan
    0.41
    Good
    0.41
    Buddy
    0.41
     giornata
    0.41
    Activations Density 0.055%

    No Known Activations