© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145936
    Prev
    Next
    INDEX
    Explanations

    linked data

    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_18_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
    headers
    0.47
    MAD
    0.46
     Мини
    0.45
    лки
    0.44
    ᱽ
    0.44
    qus
    0.43
    esthetics
    0.43
    quele
    0.43
     सिराज
    0.42
    ш
    0.42
    POSITIVE LOGITS
     be
    0.45
     extracurricular
    0.43
    感激
    0.43
     b
    0.42
    >');
    0.41
    的基础
    0.41
     NCAA
    0.41
     crim
    0.40
     می‌کنند
    0.40
     life
    0.39
    Activations Density 0.000%

    No Known Activations