© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237291
    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_32_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
     Среди
    0.38
    分野
    0.37
    文学
    0.36
     Literary
    0.36
    文學
    0.36
    Ủ
    0.36
    鲈
    0.36
    ائے
    0.35
     đáo
    0.35
    Авто
    0.34
    POSITIVE LOGITS
    ׳
    0.39
     subcellular
    0.37
    κτήθηκε
    0.35
    🦄
    0.35
     Reaction
    0.34
    PY
    0.34
     unicorn
    0.34
     ধারাবাহিক
    0.34
    عل
    0.34
     नं
    0.33
    Activations Density 0.000%

    No Known Activations