© 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
    2. Gemma-3-27B-IT
    3. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 81766
    Prev
    Next
    INDEX
    Explanations

    roots and their continuation

    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
    the
    2.50
    t
    1.94
    ad
    1.88
    p
    1.81
    ’
    1.65
    b
    1.59
    m
    1.58
    c
    1.55
    it
    1.47
    ne
    1.46
    POSITIVE LOGITS
    ру
    1.79
     insectes
    1.60
     can
    1.58
    ва
    1.58
     are
    1.55
     ماشینونه
    1.48
    ຜະລິດຕະພັນ
    1.41
     efficaces
    1.41
     bạn
    1.39
    ご飯
    1.38
    Activations Density 0.003%

    No Known Activations