© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7553
    Prev
    Next
    INDEX
    Explanations

    xml elements and attributes

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     handed
    0.40
    handed
    0.37
     girl
    0.37
    र्श
    0.36
     chicas
    0.35
    桡
    0.35
     ecology
    0.35
     discouraging
    0.35
    ц
    0.35
     স্পষ্টভাবে
    0.34
    POSITIVE LOGITS
    '`
    0.33
     Dell
    0.33
    Dell
    0.33
    Superman
    0.33
    uge
    0.32
     Edmond
    0.32
     médian
    0.32
    hore
    0.31
    Nana
    0.31
    Kong
    0.31
    Activations Density 0.009%

    No Known Activations