© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90023
    Prev
    Next
    INDEX
    Explanations

    Let's Encrypt

    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_3_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
    م
    0.79
     interesantes
    0.75
     empêcher
    0.71
     atteindre
    0.70
     αλλά
    0.69
     épouse
    0.69
     appelez
    0.69
     νέ
    0.68
     étapes
    0.68
     eradic
    0.68
    POSITIVE LOGITS
    t
    0.78
    al
    0.72
    3
    0.70
    in
    0.68
    0
    0.67
    $
    0.67
     Workshop
    0.63
     Cent
    0.62
     Data
    0.61
     Results
    0.61
    Activations Density 0.003%

    No Known Activations