© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34205
    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_31_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
     wipers
    0.35
     banners
    0.34
     woods
    0.33
    琰
    0.33
     Chag
    0.33
     printable
    0.33
     Stap
    0.33
     tè
    0.33
     files
    0.32
    facet
    0.32
    POSITIVE LOGITS
    جري
    0.38
    relaxed
    0.35
     reverence
    0.34
    Kah
    0.34
     해외
    0.34
     कोहली
    0.34
     dok
    0.33
     decreased
    0.33
    騫
    0.33
     चर्च
    0.33
    Activations Density 0.000%

    No Known Activations