© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77981
    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
     lur
    0.40
    咄
    0.40
     ling
    0.37
     })
    0.37
     pł
    0.37
    يتر
    0.37
     "@/
    0.36
    루
    0.36
    क्षणिक
    0.35
    잽
    0.35
    POSITIVE LOGITS
    Balanced
    0.36
    partite
    0.34
     incend
    0.33
    tbl
    0.33
    obac
    0.33
     Upstairs
    0.33
    flat
    0.33
    murder
    0.33
    歓迎
    0.32
    aremos
    0.32
    Activations Density 0.000%

    No Known Activations