© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203826
    Prev
    Next
    INDEX
    Explanations

    Paysenger requires users to 'burn' tokens

    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_6_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
    '
    0.37
    с
    0.32
    ריה
    0.29
    اً
    0.29
    -
    0.29
    ियो
    0.29
    은
    0.29
    לים
    0.28
    มอ
    0.28
    йда
    0.28
    POSITIVE LOGITS
    n
    0.52
    l
    0.44
    as
    0.44
    g
    0.43
    ur
    0.43
    u
    0.42
    ar
    0.39
    ul
    0.38
    v
    0.37
    và
    0.37
    Activations Density 0.000%

    No Known Activations