© 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. 201797
    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
     Somalia
    0.40
    찔
    0.38
     syndrome
    0.38
     दै
    0.37
     புரா
    0.37
    cek
    0.36
     सोना
    0.36
     असलेली
    0.36
     आहे
    0.36
    遺
    0.36
    POSITIVE LOGITS
     something
    0.39
     marshall
    0.38
    iped
    0.37
     cyclo
    0.37
     kinship
    0.37
    ishman
    0.37
     ਰਾ
    0.35
    醣
    0.35
    何か
    0.34
     properties
    0.33
    Activations Density 0.000%

    No Known Activations