© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133797
    Prev
    Next
    INDEX
    Explanations

    The Verge

    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_6_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
    ovány
    1.23
    АТ
    0.97
    РА
    0.93
    기와
    0.92
    avasena
    0.91
    ЕВ
    0.91
    Բ
    0.91
    Ｂ
    0.90
    까
    0.89
    ЕН
    0.89
    POSITIVE LOGITS
     with
    1.34
     was
    1.30
     of
    1.21
     and
    1.19
     be
    1.16
     is
    1.16
     has
    1.10
     from
    1.04
    ,
    1.02
    ли
    1.01
    Activations Density 0.000%

    No Known Activations