© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16726
    Prev
    Next
    INDEX
    Explanations

    class declaration names

    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_15_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
    details
    0.40
    ’
    0.39
    package
    0.35
    zu
    0.35
    blog
    0.35
    (
    0.34
    Bulletin
    0.34
    Bo
    0.34
     Bolet
    0.34
    '
    0.34
    POSITIVE LOGITS
    ک
    0.41
     우리는
    0.41
     thc
    0.41
     junho
    0.40
    к
    0.40
     uranium
    0.39
     chúng
    0.38
     אנחנו
    0.38
     он
    0.38
     uchun
    0.38
    Activations Density 0.001%

    No Known Activations