© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42841
    Prev
    Next
    INDEX
    Explanations

    sage publications and tandfonline

    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
    Um
    0.54
    Agora
    0.53
    ited
    0.52
    Tact
    0.52
    ور
    0.50
     زخم
    0.50
    overs
    0.50
    ῴ
    0.50
    plated
    0.49
    ῶν
    0.49
    POSITIVE LOGITS
     Gutiérrez
    0.53
    ↵↵
    0.51
     októ
    0.51
     Н
    0.50
    ハ
    0.50
     October
    0.50
     Kitts
    0.49
    ključ
    0.49
     Cous
    0.49
     först
    0.48
    Activations Density 0.000%

    No Known Activations