© 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
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 387
    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
     '/'
    2.96
    ان
    2.85
    ä
    2.70
    n
    2.70
    ק
    2.66
    probably
    2.65
     lleno
    2.51
    p
    2.49
    st
    2.46
    ر
    2.44
    POSITIVE LOGITS
     chances
    2.53
     intrepid
    2.47
     palco
    2.42
    ień
    2.35
    cursion
    2.34
    Corporate
    2.29
     NSUTF
    2.29
     стен
    2.25
    ا
    2.24
     Corporate
    2.22
    Activations Density 0.010%

    No Known Activations