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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198923
    Prev
    Next
    INDEX
    Explanations

    prep time or is prepped

    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_12_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
     Пра
    0.44
     воен
    0.43
     Кри
    0.43
     \%$,
    0.42
     soutenir
    0.41
     Prendre
    0.41
     Коло
    0.41
    воен
    0.41
     Сим
    0.40
     निदेश
    0.39
    POSITIVE LOGITS
    IG
    0.45
    ggplot
    0.45
    Florida
    0.45
    Alban
    0.44
    AR
    0.43
    ✿
    0.42
    Arabic
    0.41
    AL
    0.40
    OR
    0.40
    Baik
    0.40
    Activations Density 0.002%

    No Known Activations