© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105992
    Prev
    Next
    INDEX
    Explanations

    slurry

    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
    ad
    1.68
    स
    1.37
    ar
    1.36
    an
    1.27
    the
    1.27
    A
    1.19
    ਸ
    1.16
    it
    1.12
    ORT
    1.12
    ב
    1.12
    POSITIVE LOGITS
    '
    1.19
             
    1.09
    ↵
    1.07
     ﺍ
    1.01
     retorted
    1.01
     strony
    0.96
     истины
    0.95
    เรา
    0.94
     ребенок
    0.94
    ﺭ
    0.94
    Activations Density 0.000%

    No Known Activations