© 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. 159678
    Prev
    Next
    INDEX
    Explanations

    Afton Family or convincing

    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
    ר
    1.41
    ↵
    1.23
    ر
    1.07
    ↵↵
    1.03
    人
    1.02
     Northeastern
    0.91
     Vail
    0.89
     board
    0.87
     democratization
    0.87
     minimize
    0.86
    POSITIVE LOGITS
    其他
    1.48
    $+
    1.27
    0
    1.27
    y
    1.12
    դ
    1.12
    ～。
    1.09
    ၅
    1.07
    க்கு
    1.06
    ۔
    1.06
     immagine
    1.03
    Activations Density 0.000%

    No Known Activations