© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110126
    Prev
    Next
    INDEX
    Explanations

    Marcel duchamp, proust, marcelo

    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
    و
    1.54
     of
    1.41
    tting
    1.12
    ได้
    1.02
    tta
    1.02
    ح
    1.02
    د
    1.01
    0.97
    ере
    0.96
    就
    0.93
    POSITIVE LOGITS
    ти
    1.56
    s
    1.34
    el
    1.34
    arı
    1.30
    ill
    1.29
    in
    1.22
    il
    1.21
    ed
    1.16
    ᱗
    1.14
    ing
    1.13
    Activations Density 0.000%

    No Known Activations