© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176509
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structures

    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_20_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
    铤
    0.39
    鈮
    0.38
    Lycodon
    0.37
    蹊
    0.36
    metter
    0.35
    钞
    0.35
    SIBLE
    0.35
    
    0.34
    !--
    0.34
    anyika
    0.34
    POSITIVE LOGITS
     էին
    0.44
    px
    0.39
     був
    0.38
     AI
    0.37
     우
    0.37
     էր
    0.37
    AI
    0.36
     古
    0.35
     الس
    0.34
     decay
    0.34
    Activations Density 0.000%

    No Known Activations