© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 844
    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
     må
    0.16
     pasó
    0.16
     vå
    0.15
     nå
    0.15
     intoxicating
    0.15
    ᑉ
    0.14
     vă
    0.14
     saker
    0.14
     betyd
    0.14
     excit
    0.14
    POSITIVE LOGITS
    0.17
     coined
    0.16
      
    0.16
    С
    0.15
    ב
    0.15
     प्रीपेड
    0.15
    roger
    0.15
    chk
    0.15
     К
    0.15
    [:,
    0.15
    Activations Density 0.573%

    No Known Activations