© 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. 109956
    Prev
    Next
    INDEX
    Explanations

    yin and yang

    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
    ن
    1.73
    س
    1.66
    ل
    1.29
    л
    1.24
     for
    1.23
     to
    1.18
    ित
    1.18
    ش
    1.16
     with
    1.15
    ס
    1.12
    POSITIVE LOGITS
    il
    1.24
    X
    1.16
    EP
    1.13
    ance
    1.09
    '
    1.06
    P
    1.05
    ,
    1.04
     a
    1.03
     auta
    1.02
    0
    0.99
    Activations Density 0.000%

    No Known Activations