© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40834
    Prev
    Next
    INDEX
    Explanations

    table of contents or index

    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_3_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
    تری
    0.75
    ু
    0.72
    ческие
    0.72
    지에
    0.70
    телем
    0.69
    tı
    0.69
    mış
    0.68
    یم
    0.68
    ینک
    0.67
    ясь
    0.67
    POSITIVE LOGITS
    d
    0.91
    ad
    0.84
    我
    0.82
    vollen
    0.80
     Ukraj
    0.78
    O
    0.77
    dag
    0.73
     combinatie
    0.73
     verhaal
    0.71
     lijn
    0.71
    Activations Density 0.001%

    No Known Activations