© 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. 3895
    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
     fertilized
    2.78
    되는
    2.71
     바랍니다
    2.58
     extinct
    2.54
    इ
    2.51
     raken
    2.48
     ใ
    2.46
     eclipsed
    2.46
    ा
    2.43
     quadrants
    2.42
    POSITIVE LOGITS
    p
    2.76
    m
    2.74
    bär
    2.68
     scrollTop
    2.65
    mitted
    2.61
    ための
    2.58
     এজন্য
    2.58
     UIAlert
    2.57
    રસ
    2.55
    pinephrine
    2.50
    Activations Density 0.020%

    No Known Activations