© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29580
    Prev
    Next
    INDEX
    Explanations

    EV brands and models

    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_40_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
     öner
    0.42
    मेद
    0.39
     مؤ
    0.38
    넴
    0.36
     Cabinet
    0.35
     funzione
    0.34
    &)
    0.34
    开心
    0.34
    ψ
    0.34
     Purpose
    0.34
    POSITIVE LOGITS
     Hyundai
    0.63
     Buick
    0.60
     Chevrolet
    0.59
    Hyundai
    0.58
     Kia
    0.57
    Nissan
    0.57
     Acura
    0.57
     Nissan
    0.55
     Cadillac
    0.55
    Tesla
    0.55
    Activations Density 0.005%

    No Known Activations