© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81835
    Prev
    Next
    INDEX
    Explanations

    length / options

    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_0_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
    y
    1.81
    uğu
    1.48
     rapat
    1.41
    us
    1.30
    ۵
    1.30
    k
    1.28
    hah
    1.27
    h
    1.24
    ান
    1.23
    ución
    1.23
    POSITIVE LOGITS
    يل
    1.31
    с
    1.19
    ване
    1.17
    ibly
    1.03
     in
    1.02
    ítás
    1.00
    ш
    0.99
     for
    0.98
    менно
    0.98
    isatie
    0.98
    Activations Density 0.002%

    No Known Activations