© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250178
    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_56_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
    異
    0.37
    락
    0.31
     paradoxical
    0.30
    真
    0.30
    人和
    0.30
    异
    0.30
    🛫
    0.30
    кай
    0.29
    Metaxy
    0.29
    航空
    0.29
    POSITIVE LOGITS
     Spre
    0.35
    ieder
    0.34
    stances
    0.34
     времена
    0.34
     T
    0.32
     Du
    0.32
    tedir
    0.32
    lerde
    0.32
     L
    0.31
    ude
    0.31
    Activations Density 0.000%

    No Known Activations