© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109873
    Prev
    Next
    INDEX
    Explanations

    caustics dancing

    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_2_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
    t
    1.27
    ت
    1.19
    <0x80>
    1.16
    the
    1.16
    n
    1.06
    '
    1.06
    thed
    1.02
    ாரா
    1.00
    。
    1.00
     приготов
    0.98
    POSITIVE LOGITS
     to
    1.48
    리
    1.45
    ,
    1.40
    し
    1.24
    2
    1.16
    are
    1.13
    い
    1.12
    ни
    1.09
    ри
    1.05
    ות
    1.05
    Activations Density 0.001%

    No Known Activations