© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56349
    Prev
    Next
    INDEX
    Explanations

    a little indication of

    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_11_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
    \
    0.76
     kosakata
    0.73
    ности
    0.66
    棌
    0.64
    ுகிறது
    0.63
     okra
    0.61
    ゴルフクラブ
    0.60
    㗁
    0.59
    ാന്‍
    0.58
    िग
    0.58
    POSITIVE LOGITS
    皇
    0.68
    ﻟ
    0.64
     Londres
    0.62
    ﻄ
    0.62
     بينما
    0.57
    right
    0.56
    嗘
    0.55
    9
    0.55
    ﺒ
    0.53
     figlio
    0.52
    Activations Density 0.003%

    No Known Activations