© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36894
    Prev
    Next
    INDEX
    Explanations

    onsen, onyx, STEAM

    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
    基づ
    0.78
    ೀಯ
    0.74
    ط
    0.74
     hamil
    0.73
    اسي
    0.70
    ма
    0.68
    ква
    0.67
    }/>
    0.67
    полни
    0.67
    اي
    0.66
    POSITIVE LOGITS
     on
    0.86
    on
    0.79
    ot
    0.75
    AO
    0.73
     are
    0.72
    You
    0.69
    os
    0.66
    il
    0.65
    o
    0.65
    od
    0.64
    Activations Density 0.007%

    No Known Activations