© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27243
    Prev
    Next
    INDEX
    Explanations

    programs followed by ':'

    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_10_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
     ñ
    0.32
     an
    0.29
    å
    0.26
    és
    0.26
     le
    0.26
    il
    0.25
     ð
    0.25
     of
    0.24
    ä
    0.24
     å
    0.24
    POSITIVE LOGITS
    Ти
    0.33
    Program
    0.30
    Ко
    0.30
    При
    0.30
    Від
    0.29
    Спо
    0.29
    Ма
    0.29
    Со
    0.29
    Фу
    0.29
    Fl
    0.28
    Activations Density 0.008%

    No Known Activations