© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134824
    Prev
    Next
    INDEX
    Explanations

    Olina, Lucas, Wood, Fay

    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_1_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
     to
    1.27
     been
    1.11
     be
    1.04
     that
    1.04
     with
    1.02
     y
    0.95
     for
    0.94
     can
    0.91
     you
    0.91
    の見
    0.86
    POSITIVE LOGITS
    the
    1.20
    các
    1.04
    и
    1.02
    و
    0.96
    t
    0.95
    د
    0.95
    k
    0.95
    گ
    0.94
    ی
    0.91
    ков
    0.88
    Activations Density 0.000%

    No Known Activations