© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142806
    Prev
    Next
    INDEX
    Explanations

    legal and policy reforms

    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_0_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
    on
    1.73
    r
    1.70
    at
    1.66
    an
    1.65
    il
    1.58
    or
    1.52
    ad
    1.52
    et
    1.50
    K
    1.48
    ap
    1.46
    POSITIVE LOGITS
    ח
    1.91
    ס
    1.71
    ו
    1.70
     estadísticas
    1.68
     ﺍﻟ
    1.62
     académ
    1.59
     vultures
    1.59
     futuras
    1.57
     поги
    1.52
    د
    1.52
    Activations Density 0.000%

    No Known Activations