© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37247
    Prev
    Next
    INDEX
    Explanations

    virus, C minor, C major, CFrame

    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
    s
    0.77
    name
    0.77
    northern
    0.76
    r
    0.75
    上
    0.70
    sk
    0.68
    sinh
    0.68
    re
    0.68
    問題
    0.67
    体
    0.67
    POSITIVE LOGITS
    \
    0.87
    <0x80>
    0.77
     видеть
    0.70
    0
    0.70
     счета
    0.67
    aków
    0.67
    '
    0.67
    akn
    0.66
    িকভাবে
    0.66
    (.*
    0.65
    Activations Density 0.002%

    No Known Activations