© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6963
    Prev
    Next
    INDEX
    Explanations

    parse JSON/XML as

    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_40_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
    лии
    0.45
    numeric
    0.41
     塩
    0.41
    VALUES
    0.41
    微分
    0.38
     bituminous
    0.38
    numerical
    0.38
    敔
    0.38
     diferenciales
    0.37
    values
    0.37
    POSITIVE LOGITS
     sling
    0.53
    sling
    0.49
     Sling
    0.47
    text
    0.40
    ID
    0.39
    enco
    0.39
     Capp
    0.39
     ID
    0.39
     text
    0.39
    apanam
    0.38
    Activations Density 0.031%

    No Known Activations