© 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. 14543
    Prev
    Next
    INDEX
    Explanations

    Angular

    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
     prediction
    0.51
    〒
    0.50
    OTO
    0.49
    ᵔ
    0.48
     teapot
    0.47
     ổ
    0.47
     kew
    0.47
     shavings
    0.46
    ênt
    0.46
     phenotype
    0.46
    POSITIVE LOGITS
     جميع
    0.54
     Messenger
    0.52
     искус
    0.50
     FIVE
    0.49
    ischer
    0.47
    蹑
    0.47
     Divine
    0.47
     Brotherhood
    0.47
    messenger
    0.47
     Moses
    0.47
    Activations Density 0.003%

    No Known Activations