© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138749
    Prev
    Next
    INDEX
    Explanations

    laws and states

    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_46_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
     ನಿಯ
    0.43
    <unused38>
    0.40
     নিয়
    0.40
    International
    0.35
    Susan
    0.35
    ✤
    0.35
     국제
    0.34
    
    0.34
     International
    0.33
    General
    0.33
    POSITIVE LOGITS
     users
    0.50
     campers
    0.47
     کاربران
    0.46
    users
    0.46
     उद्यमियों
    0.43
     producers
    0.42
     utenti
    0.42
     userRepository
    0.42
     ребята
    0.41
    म्मेदारी
    0.41
    Activations Density 0.002%

    No Known Activations