© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45495
    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_10_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
    대
    0.55
     erc
    0.54
     anunci
    0.53
     alkaloids
    0.53
    Мар
    0.49
    مد
    0.47
    lari
    0.46
     asesin
    0.46
    说
    0.46
    that
    0.46
    POSITIVE LOGITS
    BOAT
    0.50
    BITS
    0.49
    ATO
    0.49
    AMM
    0.49
    佽
    0.48
     Mourinho
    0.48
    SOFT
    0.47
    BOSS
    0.47
    ongrass
    0.47
    ITTER
    0.46
    Activations Density 0.000%

    No Known Activations