© 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. 84291
    Prev
    Next
    INDEX
    Explanations

    Bosch, Ortega, Briggs names

    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
    il
    1.79
    w
    1.72
    ag
    1.68
    ast
    1.58
    ri
    1.51
    r
    1.44
    ar
    1.43
    art
    1.38
    he
    1.38
    ins
    1.37
    POSITIVE LOGITS
    是
    1.75
    ج
    1.68
    ي
    1.59
    س
    1.53
    د
    1.51
    를
    1.51
    。
    1.48
    在
    1.48
    は
    1.45
    اي
    1.45
    Activations Density 0.000%

    No Known Activations