© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207103
    Prev
    Next
    INDEX
    Explanations

    courier, give/services

    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_10_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
    ability
    0.67
    bordered
    0.63
    compared
    0.61
    ễ
    0.60
    д
    0.60
    ävä
    0.59
    applicable
    0.59
    ır
    0.57
    ed
    0.57
    unstyled
    0.57
    POSITIVE LOGITS
    在
    0.63
    但在
    0.57
     aber
    0.56
    但是
    0.55
     في
    0.54
    ரஜன்
    0.54
     但
    0.53
     in
    0.52
     الذي
    0.52
     însă
    0.52
    Activations Density 0.000%

    No Known Activations