© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 200020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
     سعی
    0.56
    ៨
    0.51
    ᄌ
    0.49
    齟
    0.48
    inputFields
    0.48
    getTargetContext
    0.47
     wronged
    0.45
    fdPar
    0.45
    atoire
    0.45
    ürdig
    0.44
    POSITIVE LOGITS
     impressão
    0.48
    '
    0.47
     ആണ്
    0.46
    شر
    0.45
    SAND
    0.44
    مان
    0.44
     Vib
    0.43
     erős
    0.43
     prob
    0.42
    आईपी
    0.41
    Activations Density 0.000%

    No Known Activations