© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2032
    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
    ה
    3.00
    t
    2.58
     toString
    2.58
     toasted
    2.54
    ва
    2.53
     tratti
    2.48
     altro
    2.47
    ECH
    2.47
    
    2.46
    न
    2.42
    POSITIVE LOGITS
    ो
    2.92
    و
    2.78
    ી
    2.52
     sprawl
    2.51
     cmap
    2.49
    adays
    2.49
    তে
    2.47
    !\!\
    2.46
    ین
    2.43
    cellaneous
    2.42
    Activations Density 0.011%

    No Known Activations