© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35003
    Prev
    Next
    INDEX
    Explanations

    json structure

    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
    '});
    0.51
     basiert
    0.50
     вече
    0.49
     externe
    0.48
     shortcomings
    0.48
    ுள்ளார்
    0.47
    ம்
    0.47
     onderdeel
    0.46
    щена
    0.46
     orchestrated
    0.46
    POSITIVE LOGITS
    ä
    0.78
    x
    0.70
    명
    0.66
    са
    0.65
    ки
    0.65
    श
    0.64
    proteins
    0.64
    persons
    0.63
    ку
    0.63
    по
    0.62
    Activations Density 0.000%

    No Known Activations