© 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. 45934
    Prev
    Next
    INDEX
    Explanations

    granola with fruit or yogurt

    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
     práctico
    0.57
    upp
    0.55
    。(
    0.55
     επίσης
    0.55
     。
    0.54
    uje
    0.54
     。,
    0.54
    m
    0.52
    o
    0.51
    ú
    0.51
    POSITIVE LOGITS
    ری
    0.72
    ?
    0.71
    あれば
    0.68
     digitization
    0.67
    ﹰ
    0.66
     forbidden
    0.63
    لی
    0.62
    ہ
    0.62
    funcion
    0.62
     cleanser
    0.61
    Activations Density 0.001%

    No Known Activations