© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24423
    Prev
    Next
    INDEX
    Explanations

    natural language and manner

    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_10_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
    t
    1.33
    in
    0.96
    S
    0.87
    d
    0.84
    de
    0.80
    v
    0.77
    ت
    0.75
    د
    0.73
    time
    0.73
    A
    0.73
    POSITIVE LOGITS
     mecz
    0.74
     spune
    0.73
     pierwszy
    0.72
     пишу
    0.71
     بیټ
    0.70
     primeiro
    0.69
    クリニック
    0.68
     seventh
    0.66
     pierws
    0.65
     clínica
    0.65
    Activations Density 0.018%

    No Known Activations