© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80107
    Prev
    Next
    INDEX
    Explanations

    defects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    нику
    0.41
    𝚋
    0.39
    GOND
    0.38
    मंद
    0.37
     vulcan
    0.37
     miền
    0.37
     vuccanti
    0.37
     Ester
    0.37
    千
    0.37
    绒
    0.36
    POSITIVE LOGITS
     defects
    0.44
     defective
    0.42
     defect
    0.42
     Defects
    0.41
     heavy
    0.39
     workout
    0.39
     desktop
    0.38
     applying
    0.37
     Reis
    0.36
    reven
    0.36
    Activations Density 0.002%

    No Known Activations