© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118131
    Prev
    Next
    INDEX
    Explanations

    code blocks with true/false

    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_27_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
    subheader
    0.36
     background
    0.35
    
    0.34
    Commission
    0.34
     구분
    0.33
     screens
    0.32
     Commission
    0.32
     Criterion
    0.32
    background
    0.32
    Formula
    0.32
    POSITIVE LOGITS
    elben
    0.40
     blacksmith
    0.38
    ೖ
    0.38
    yenne
    0.38
     आयुर्वेदिक
    0.36
    leyball
    0.36
    iedades
    0.35
     Nobody
    0.34
    พัน
    0.34
     พระเจ้า
    0.34
    Activations Density 0.000%

    No Known Activations