© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135192
    Prev
    Next
    INDEX
    Explanations

    words with specific sounds

    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_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
    鄭
    0.42
     Nanjing
    0.41
     maritime
    0.39
     naval
    0.38
     中国
    0.38
     infra
    0.38
     explorers
    0.38
     chinese
    0.37
    的发
    0.37
     Chinese
    0.36
    POSITIVE LOGITS
    met
    0.41
    animate
    0.41
     Hol
    0.40
     Pil
    0.38
    锑
    0.38
    疖
    0.37
     Toscana
    0.37
    BusinessType
    0.37
    Hol
    0.36
    pix
    0.36
    Activations Density 0.033%

    No Known Activations