© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62109
    Prev
    Next
    INDEX
    Explanations

    ribbon or ribbons

    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
    喡
    0.64
     Clauses
    0.61
     charters
    0.58
    নাম
    0.57
     która
    0.56
     documentaries
    0.56
     باك
    0.55
     parades
    0.55
     which
    0.55
     которая
    0.55
    POSITIVE LOGITS
     Chesapeake
    0.59
    ordable
    0.58
     Riemannian
    0.58
    el
    0.57
    elder
    0.52
    "
    0.52
    ie
    0.52
    us
    0.52
    ̌
    0.50
     Euclidean
    0.50
    Activations Density 0.001%

    No Known Activations