© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204653
    Prev
    Next
    INDEX
    Explanations

    frontend development

    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_6_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
     for
    1.23
    for
    1.07
     (
    1.03
    0.96
     For
    0.85
    ním
    0.84
    cción
    0.84
     busted
    0.83
     verand
    0.83
    ాను
    0.79
    POSITIVE LOGITS
    ר
    1.59
    ות
    1.42
    र
    1.38
    ла
    1.21
    ตัวเอง
    1.16
    8
    1.16
    Μ
    1.15
    ז
    1.12
    عرف
    1.10
    트
    1.10
    Activations Density 0.001%

    No Known Activations