© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84218
    Prev
    Next
    INDEX
    Explanations

    rowers, boats, death row

    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_0_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
    ä
    2.06
    d
    1.79
    t
    1.72
    u
    1.60
    и
    1.45
    ни
    1.45
    ના
    1.43
    i
    1.30
    у
    1.27
    uí
    1.27
    POSITIVE LOGITS
    ق
    1.69
     I
    1.68
    ك
    1.59
    س
    1.57
    স
    1.49
    स
    1.48
     (
    1.32
     A
    1.29
    ক
    1.22
     the
    1.21
    Activations Density 0.005%

    No Known Activations