© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13793
    Prev
    Next
    INDEX
    Explanations

    thalam, RX, rage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    ان
    0.11
    anzi
    0.11
    ixir
    0.11
    ⌵
    0.10
    ढ़
    0.10
    icc
    0.10
    得以
    0.10
     entrepreneur
    0.10
    бва
    0.10
    ikopter
    0.10
    POSITIVE LOGITS
     ترین
    0.11
     ポ
    0.11
    fetch
    0.11
     बट
    0.11
     बहस
    0.11
     czynności
    0.11
     služby
    0.10
     Gage
    0.10
    ascimento
    0.10
    ഞ്ചി
    0.10
    Activations Density 0.009%

    No Known Activations