© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44464
    Prev
    Next
    INDEX
    Explanations

    chess players and drawish positions

    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_13_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
    avano
    0.55
    اني
    0.54
    拈
    0.52
    انی
    0.51
    ﻮ
    0.50
    orgen
    0.48
    ﺎ
    0.48
    org
    0.48
    ів
    0.47
    ván
    0.47
    POSITIVE LOGITS
    ᱓
    0.54
     acidic
    0.54
    Restaurants
    0.53
     attentive
    0.52
     ஆய்வு
    0.50
    ícias
    0.50
     ০
    0.50
    LS
    0.49
    ต้
    0.48
    Drinking
    0.48
    Activations Density 0.000%

    No Known Activations