© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111904
    Prev
    Next
    INDEX
    Explanations

    rundown of

    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_2_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
    ت
    2.28
    त
    1.52
    ת
    1.46
    m
    1.40
    т
    1.37
    H
    1.36
    V
    1.29
    م
    1.26
    to
    1.23
    W
    1.23
    POSITIVE LOGITS
    ના
    1.24
     ότι
    1.07
     is
    0.99
     edilmesi
    0.98
     opravdu
    0.98
     incentivize
    0.96
    いた
    0.95
     σχετικά
    0.93
    abilir
    0.91
     prijatel
    0.91
    Activations Density 0.001%

    No Known Activations