© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3777
    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
    r
    2.02
    此事
    1.90
    क
    1.86
    人员
    1.74
    rer
    1.73
    ll
    1.67
     economies
    1.58
    تدائي
    1.55
     gladly
    1.55
    
    1.53
    POSITIVE LOGITS
    AN
    2.21
     hérit
    2.10
     partire
    2.04
     соединения
    2.03
     siedz
    2.03
    OND
    2.00
    IN
    1.98
     partir
    1.98
     thiol
    1.91
     bunyi
    1.91
    Activations Density 0.001%

    No Known Activations