© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198968
    Prev
    Next
    INDEX
    Explanations

    range, comma, len, n

    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_12_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
    П
    0.62
    FETCH
    0.59
     письмо
    0.58
     становятся
    0.57
     لیګ
    0.55
     Desarrollo
    0.54
    骧
    0.54
    튼
    0.54
     වඩා
    0.53
     Tarn
    0.53
    POSITIVE LOGITS
    at
    0.54
     rightful
    0.51
    ay
    0.50
     l
    0.49
    re
    0.49
    an
    0.47
    ance
    0.47
    ights
    0.47
     bahagian
    0.47
    ana
    0.46
    Activations Density 0.001%

    No Known Activations