© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98927
    Prev
    Next
    INDEX
    Explanations

    intellectual disability

    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_14_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
    i
    0.56
    לי
    0.54
    fault
    0.54
    غا
    0.52
    ელია
    0.52
     اتارنا
    0.51
    선
    0.49
    वरिश
    0.49
    Га
    0.49
    Від
    0.48
    POSITIVE LOGITS
    める
    0.52
    thur
    0.50
    USTER
    0.48
     Plank
    0.48
     realizzare
    0.47
     பெண்ண
    0.47
    matically
    0.45
    IY
    0.45
    ₚ
    0.45
    üng
    0.45
    Activations Density 0.001%

    No Known Activations