© 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-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 994
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     acronym
    3.19
     Rxe
    3.09
    cribing
    2.95
     отсут
    2.68
     fashioned
    2.62
    هل
    2.57
    挝
    2.43
    ek
    2.41
    我现在
    2.35
    باز
    2.34
    POSITIVE LOGITS
    ﺝ
    2.79
    ために
    2.74
    во
    2.68
    lay
    2.61
    வும்
    2.47
    $.\
    2.46
    需
    2.45
    createSprite
    2.43
    र
    2.41
     mẽ
    2.41
    Activations Density 0.003%

    No Known Activations