© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197829
    Prev
    Next
    INDEX
    Explanations

    diferencias clave

    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_12_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
    ário
    0.51
    ól
    0.49
    arii
    0.49
    nr
    0.48
    ării
    0.48
    duire
    0.47
    ito
    0.46
     its
    0.46
    {'
    0.46
    otron
    0.46
    POSITIVE LOGITS
     молоко
    0.63
    ע
    0.59
    ات
    0.58
    فات
    0.55
    ة
    0.55
     также
    0.54
     geweld
    0.54
    ল্যান্ডের
    0.52
     لما
    0.52
     секре
    0.52
    Activations Density 0.000%

    No Known Activations