© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164675
    Prev
    Next
    INDEX
    Explanations

    supersize

    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_13_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
    ↵↵
    0.59
     PN
    0.59
     policy
    0.55
     pandemic
    0.55
     trails
    0.55
     primates
    0.55
     degrees
    0.53
     issues
    0.52
     extracting
    0.52
     issue
    0.52
    POSITIVE LOGITS
    ၌
    0.58
    itrile
    0.57
    Alone
    0.54
    urpose
    0.52
    ⚈
    0.51
     Algun
    0.50
    Sullivan
    0.50
     മാത്രം
    0.50
    átil
    0.50
    atás
    0.50
    Activations Density 0.000%

    No Known Activations