© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213337
    Prev
    Next
    INDEX
    Explanations

    из-за

    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_5_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
     you
    1.37
    im
    1.35
    ہ
    1.35
    um
    1.32
     a
    1.29
    지
    1.28
    R
    1.27
    ים
    1.20
    X
    1.20
    q
    1.14
    POSITIVE LOGITS
    ه
    0.95
     cuadro
    0.92
     (
    0.92
    лно
    0.91
    кта
    0.89
    iamo
    0.88
    ПО
    0.87
     строк
    0.87
     правило
    0.85
     ребенок
    0.84
    Activations Density 0.000%

    No Known Activations