© 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. 137206
    Prev
    Next
    INDEX
    Explanations

    Grand Unified Theories

    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
     atthakath
    0.59
     لوب
    0.58
     길
    0.57
     vuurp
    0.54
     bors
    0.54
     있을
    0.52
     уравнение
    0.52
     trenut
    0.51
    ("("
    0.51
     ස
    0.50
    POSITIVE LOGITS
     payer
    0.56
    Become
    0.56
    ைகளால்
    0.55
    Celebrate
    0.50
    Ter
    0.48
     régulièrement
    0.48
    Celebrating
    0.46
    Our
    0.46
    કારો
    0.46
    ಯ್ಯ
    0.46
    Activations Density 0.000%

    No Known Activations