© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46485
    Prev
    Next
    INDEX
    Explanations

    driving techno

    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
    
    0.51
    ﻱ
    0.49
     ഏറ്റവും
    0.48
    URACY
    0.47
     anthracite
    0.47
    لية
    0.46
     angezeigt
    0.46
    ものです
    0.46
     отправ
    0.45
    OrderFlight
    0.45
    POSITIVE LOGITS
    ud
    0.63
    id
    0.51
    ش
    0.50
    aro
    0.49
    ق
    0.49
    els
    0.48
    ن
    0.47
     Ä
    0.47
    ubre
    0.46
    ap
    0.46
    Activations Density 0.000%

    No Known Activations