© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93802
    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_60_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
    吉
    0.42
     Жи
    0.38
     Segurança
    0.37
    Fet
    0.36
     Боль
    0.36
    いを
    0.36
    のである
    0.36
    Г
    0.36
     അങ്ങനെ
    0.35
     Ники
    0.35
    POSITIVE LOGITS
    to
    0.51
    a
    0.50
    tens
    0.48
    h
    0.47
    state
    0.42
    st
    0.41
    track
    0.41
    app
    0.41
    toll
    0.41
    শক্তি
    0.40
    Activations Density 0.000%

    No Known Activations