© 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. 123107
    Prev
    Next
    INDEX
    Explanations

    lactate

    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
    스
    0.94
    د
    0.91
    س
    0.88
    ა
    0.82
    स
    0.80
    স
    0.79
    ూ
    0.78
    ش
    0.75
    ن
    0.75
    o
    0.69
    POSITIVE LOGITS
    '
    0.83
    kunft
    0.68
    cela
    0.67
    ແ
    0.67
     Sponge
    0.66
    ha
    0.66
    螓
    0.65
     enkele
    0.63
     Mirza
    0.61
     toilette
    0.60
    Activations Density 0.001%

    No Known Activations