© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248162
    Prev
    Next
    INDEX
    Explanations

    symbols or operators

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     plus
    2.83
     Plus
    2.67
     +
    2.64
     प्लस
    2.59
    Plus
    2.56
    plus
    2.55
     PLUS
    2.55
     плюс
    2.52
     $+$
    2.50
     플러스
    2.50
    POSITIVE LOGITS
    ceğiz
    0.35
     ചെയ
    0.35
    琙
    0.35
    㕕
    0.33
    Გ
    0.33
    ardino
    0.33
    жета
    0.33
    傗
    0.32
     QText
    0.32
    侙
    0.32
    Activations Density 0.008%

    No Known Activations