© 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. 81636
    Prev
    Next
    INDEX
    Explanations

    kiss or statesmanship

    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
    ↵↵
    2.14
    l
    2.09
    r
    1.84
    ro
    1.81
    p
    1.75
    7
    1.73
    是
    1.70
    :
    1.58
    that
    1.56
    ing
    1.55
    POSITIVE LOGITS
    АЗ
    1.27
    に
    1.27
    IS
    1.25
    에
    1.24
    ርዓ
    1.23
    ა
    1.23
     أكتوبر
    1.18
    ب
    1.17
    ၀
    1.16
    ()},
    1.15
    Activations Density 0.001%

    No Known Activations