© 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. 3767
    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
     koji
    0.78
    த்தின்
    0.65
     ও
    0.64
    Efter
    0.62
    či
    0.60
     و
    0.60
    ,
    0.60
     আর
    0.60
    ።
    0.59
    સ
    0.59
    POSITIVE LOGITS
    l
    0.86
    ஔ
    0.80
    iduría
    0.78
    tbl
    0.78
     nurture
    0.74
    تام
    0.72
    cough
    0.71
    teborg
    0.70
    ገልግሎ
    0.70
    lma
    0.70
    Activations Density 0.939%

    No Known Activations