© 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. 100317
    Prev
    Next
    INDEX
    Explanations

    bowel syndrome

    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
    át
    0.61
    .}(
    0.52
    í
    0.50
    unc
    0.49
    ड़ा
    0.48
    ued
    0.47
    ائ
    0.47
    ých
    0.46
    ไม่มี
    0.46
     paved
    0.46
    POSITIVE LOGITS
    Bsky
    0.61
     préférences
    0.58
    шет
    0.57
     prestazioni
    0.56
     derivs
    0.56
    symplectic
    0.55
    椥
    0.55
    Ва
    0.54
    赉
    0.54
     прось
    0.53
    Activations Density 0.001%

    No Known Activations