© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123096
    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_37_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
     enthalten
    0.43
    嘧
    0.41
    enser
    0.38
     epithelial
    0.37
     cottura
    0.36
     đựng
    0.36
     պատ
    0.36
    辶
    0.36
    Франків
    0.36
     इच्छुक
    0.35
    POSITIVE LOGITS
    جر
    0.40
    риди
    0.38
    reverse
    0.37
    Electrical
    0.37
     رو
    0.36
     ফেব্রুয়ারি
    0.36
    ______________
    0.35
     family
    0.35
    john
    0.35
     Bundy
    0.35
    Activations Density 0.000%

    No Known Activations