© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2092
    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_12_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
    實
    0.75
     preclinical
    0.75
    followlike
    0.75
     thử
    0.75
     воспользоваться
    0.75
     praxis
    0.74
    실
    0.74
     düşünüyorum
    0.74
    লাই
    0.73
    
    0.72
    POSITIVE LOGITS
     Cowboys
    0.75
     dissolved
    0.74
     expelled
    0.74
     mouth
    0.70
     Dow
    0.70
     w
    0.69
     saffron
    0.69
     condol
    0.68
    affron
    0.68
     beans
    0.67
    Activations Density 0.004%

    No Known Activations