© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145525
    Prev
    Next
    INDEX
    Explanations

    colored description

    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_0_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
    et
    1.68
    an
    1.66
    as
    1.50
    ł
    1.48
    ab
    1.41
    v
    1.40
    ور
    1.38
    ש
    1.38
    д
    1.38
    지
    1.35
    POSITIVE LOGITS
     not
    1.29
    是
    1.27
     ي
    1.18
     Лон
    1.18
     တော့
    1.16
     الجنوب
    1.12
     الأمريكي
    1.09
    ní
    1.09
    ről
    1.08
     lijn
    1.06
    Activations Density 0.000%

    No Known Activations