© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4123
    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
    Negative Logits
    𝘔
    1.55
    𝘣
    1.43
    ன
    1.41
    Situated
    1.41
    𝔪
    1.40
    ﺱ
    1.39
     elated
    1.39
     इसे
    1.35
     брат
    1.33
    localVarHTTP
    1.32
    POSITIVE LOGITS
    t
    1.61
    un
    1.35
    εται
    1.31
    im
    1.26
     rispond
    1.26
    ्स
    1.26
    iato
    1.22
    )";
    1.21
    től
    1.18
    ially
    1.18
    Activations Density 0.005%

    No Known Activations