© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108821
    Prev
    Next
    INDEX
    Explanations

    unite people, groups, or entities

    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_2_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
    on
    1.25
    я
    1.09
    ط
    1.05
    an
    1.00
    就有
    0.98
    as
    0.97
    ता
    0.97
    ъ
    0.96
    ä
    0.95
    ך
    0.95
    POSITIVE LOGITS
     mencion
    1.13
    '
    1.10
     dupla
    1.09
     venced
    1.05
     encerr
    1.05
     deportivas
    1.05
    ↵
    1.04
     darkMode
    1.03
     searchTerm
    1.02
    。
    1.02
    Activations Density 0.000%

    No Known Activations