© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45493
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     órgãos
    0.48
    สอน
    0.46
    媝
    0.46
    тельных
    0.46
     Nac
    0.45
    க்கு
    0.45
     стоимо
    0.44
    kuu
    0.44
    躡
    0.43
     ontwikkelen
    0.43
    POSITIVE LOGITS
     sclerosis
    0.48
    ிரஸ்
    0.41
    municipal
    0.40
     oncology
    0.40
     enforceable
    0.39
     بغیر
    0.39
    しくは
    0.38
    中止
    0.38
     policies
    0.38
     timer
    0.38
    Activations Density 0.000%

    No Known Activations