© 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. 56836
    Prev
    Next
    INDEX
    Explanations

    disgruntled person or thing

    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
    ar
    0.76
    yl
    0.76
    n
    0.73
    ana
    0.73
    ter
    0.72
    yn
    0.71
    asian
    0.70
    pol
    0.69
    k
    0.69
    ran
    0.68
    POSITIVE LOGITS
     الذي
    0.56
     હોય
    0.55
    ായി
    0.53
     Weise
    0.53
     Eigenschaften
    0.53
    эс
    0.52
    Subview
    0.52
     occurrences
    0.52
    <0xEF>
    0.52
     С
    0.52
    Activations Density 0.001%

    No Known Activations