© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59327
    Prev
    Next
    INDEX
    Explanations

    technical or formal language demonstration

    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_11_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
    a
    0.57
    A
    0.52
     or
    0.48
     pract
    0.47
    ch
    0.46
    com
    0.46
    Being
    0.46
    as
    0.45
    o
    0.45
    Check
    0.45
    POSITIVE LOGITS
    fromParams
    0.46
     technologically
    0.46
    ittances
    0.46
     ನಿ
    0.46
    gradients
    0.45
     تکن
    0.45
    regulatory
    0.44
     warmest
    0.44
     డా
    0.44
     governmental
    0.43
    Activations Density 0.000%

    No Known Activations