© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152857
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     basilaires
    0.46
     spaceleft
    0.42
     мы
    0.42
    ábamos
    0.40
    $^
    0.40
    jdField
    0.40
     نوٹ
    0.39
    الصفحه
    0.38
     aident
    0.38
    اکي
    0.38
    POSITIVE LOGITS
     I
    0.74
    <em>
    0.63
     so
    0.57
     Sa
    0.57
     Wa
    0.57
     Pa
    0.56
     Κ
    0.56
     "
    0.55
     there
    0.55
     Fa
    0.55
    Activations Density 0.000%

    No Known Activations