© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    ه
    0.80
    a
    0.62
    Все
    0.60
    Os
    0.59
    Ol
    0.56
     célé
    0.55
    O
    0.54
    Ка
    0.54
    Descrição
    0.53
     uved
    0.52
    POSITIVE LOGITS
    ણી
    0.54
    ها
    0.52
    keit
    0.50
    шина
    0.48
     illusory
    0.47
     allegiance
    0.46
    つつ
    0.46
    教えて
    0.46
     Admittedly
    0.46
     earthenware
    0.45
    Activations Density 0.000%

    No Known Activations