© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81297
    Prev
    Next
    INDEX
    Explanations

    MAT, "deb https", setVisible

    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
    د
    1.77
    д
    1.60
    t
    1.45
     to
    1.28
    дят
    1.25
    d
    1.25
    c
    1.23
     for
    1.23
    g
    1.22
    ä
    1.20
    POSITIVE LOGITS
    ’
    1.86
    ;
    1.71
    ’),
    1.43
    Это
    1.34
    ﺭ
    1.34
    4
    1.32
    ın
    1.31
    2
    1.31
    Aeonium
    1.24
    К
    1.24
    Activations Density 0.000%

    No Known Activations