© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195207
    Prev
    Next
    INDEX
    Explanations

    trailforks, Cuemath calling, extended, drop handlebars, computed tomography, com tam

    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_15_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
     GeV
    0.52
     ಹಿಂದ
    0.50
     оцени
    0.50
     dover
    0.49
    碑
    0.49
    信息公示
    0.47
     зар
    0.47
     corris
    0.46
    ALI
    0.46
     FileReader
    0.46
    POSITIVE LOGITS
    성
    0.49
    ಕ
    0.46
     asientos
    0.46
     。
    0.46
     میان
    0.46
     afară
    0.45
     techniques
    0.44
    amette
    0.44
     <>
    0.44
     እንደ
    0.44
    Activations Density 0.000%

    No Known Activations