© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145072
    Prev
    Next
    INDEX
    Explanations

    research proposal

    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_18_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
    InfoPlist
    0.58
     nélkül
    0.54
    selfobj
    0.52
     组件
    0.52
     বৃত্তান্ত
    0.52
     consegn
    0.51
     Бор
    0.51
     使っ
    0.50
    Khokhlov
    0.49
    [,,"
    0.49
    POSITIVE LOGITS
    ar
    0.52
    ↵
    0.50
    in
    0.49
    water
    0.49
    는
    0.48
     perch
    0.47
    म
    0.47
    E
    0.47
    is
    0.46
    ↵↵
    0.45
    Activations Density 0.000%

    No Known Activations