© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2639
    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
     Challenge
    0.15
     Float
    0.15
     Sensitivity
    0.15
    [
    0.14
     Demand
    0.14
     или
    0.13
     sensitivity
    0.13
    Sensitivity
    0.13
    Challenge
    0.12
     Prod
    0.12
    POSITIVE LOGITS
    ፑ
    0.16
    মহাদেশ
    0.16
    merich
    0.16
    emaking
    0.16
     receding
    0.16
    เทพ
    0.16
     cluttered
    0.15
     océano
    0.15
    
    0.15
    nahi
    0.15
    Activations Density 0.459%

    No Known Activations