© 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. 213831
    Prev
    Next
    INDEX
    Explanations

    quoted text

    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
    1
    1.73
     a
    1.46
    К
    1.28
    ১৫
    1.22
    3
    1.19
    ”
    1.16
     have
    1.13
     presente
    1.09
    。\
    1.09
     présente
    1.07
    POSITIVE LOGITS
    ان
    1.29
    ע
    1.29
    ки
    1.14
    -
    0.93
    ants
    0.92
    ۰
    0.91
    0.91
    ↵
    0.90
    ες
    0.86
    係る
    0.85
    Activations Density 0.002%

    No Known Activations