© 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. 176505
    Prev
    Next
    INDEX
    Explanations

    checking conditions like 'input', 'match', 'remainder'

    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
     verurs
    0.32
    വാൻ
    0.32
    coerce
    0.28
     また
    0.28
     ល
    0.28
     やつ
    0.27
     вул
    0.26
     curviliné
    0.26
     hogi
    0.26
     liegen
    0.26
    POSITIVE LOGITS
    eem
    0.29
    ccess
    0.28
    стон
    0.28
     Acne
    0.27
    icip
    0.27
    ეხ
    0.27
    ب
    0.27
    ę
    0.27
     accesorios
    0.26
     students
    0.26
    Activations Density 0.021%

    No Known Activations