© 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. 58210
    Prev
    Next
    INDEX
    Explanations

    upset

    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
    ي
    0.84
    ı
    0.77
    ל
    0.73
    લ
    0.73
    imo
    0.71
    ž
    0.69
    ıl
    0.66
    י
    0.66
    ıma
    0.65
    ल
    0.64
    POSITIVE LOGITS
     flexion
    0.62
     policy
    0.55
    צרים
    0.55
     reducer
    0.55
    悰
    0.55
     learner
    0.54
     forgiving
    0.54
     fountain
    0.53
    LLER
    0.52
     verific
    0.52
    Activations Density 0.001%

    No Known Activations