© 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. 10013
    Prev
    Next
    INDEX
    Explanations

    Parliament, assembly, Bundestag

    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
    تش
    0.52
    )：
    0.48
    ا
    0.47
    辣
    0.45
    لز
    0.44
    採
    0.44
    笋
    0.44
    )，
    0.43
    inti
    0.43
    و
    0.43
    POSITIVE LOGITS
     Comercio
    0.60
     domést
    0.52
     sederhana
    0.52
     এসএম
    0.50
     Corporations
    0.50
     disminución
    0.50
    werten
    0.50
    Karo
    0.49
    niejs
    0.49
     Comisión
    0.48
    Activations Density 0.009%

    No Known Activations