© 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. 88381
    Prev
    Next
    INDEX
    Explanations

    letterhead formatting

    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
    the
    0.66
    lar
    0.61
    ta
    0.56
    a
    0.54
     август
    0.53
    crt
    0.53
    Ꮷ
    0.53
    did
    0.52
    ákat
    0.52
    Tecla
    0.51
    POSITIVE LOGITS
     to
    0.93
    یت
    0.83
     of
    0.75
     on
    0.73
     It
    0.71
     are
    0.70
    حة
    0.70
    هم
    0.70
    ص
    0.67
    ری
    0.66
    Activations Density 0.000%

    No Known Activations