© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89920
    Prev
    Next
    INDEX
    Explanations

    preferring better

    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_3_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
    ни
    0.88
     код
    0.88
    that
    0.84
     начало
    0.79
     устройство
    0.77
     почвы
    0.77
    ן
    0.77
     статьи
    0.77
    ۰
    0.76
     август
    0.75
    POSITIVE LOGITS
    n
    0.98
    h
    0.96
    in
    0.87
     t
    0.85
     Z
    0.80
    al
    0.79
     as
    0.78
     UP
    0.78
     V
    0.77
     R
    0.77
    Activations Density 0.000%

    No Known Activations