© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60608
    Prev
    Next
    INDEX
    Explanations

    EirGrid, EIRL, Air, Eira, aire

    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_11_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
    '
    0.62
     verdens
    0.60
     vague
    0.58
     sexually
    0.58
     wrong
    0.57
     erase
    0.57
     vagina
    0.55
     judgmental
    0.55
     resurrection
    0.55
     dishwasher
    0.54
    POSITIVE LOGITS
    s
    0.75
    in
    0.69
    ों
    0.66
    prof
    0.62
    ण
    0.60
    播
    0.59
    ের
    0.59
    I
    0.58
    سپ
    0.57
    adz
    0.55
    Activations Density 0.000%

    No Known Activations