© 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. 2657
    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
    ان
    2.06
    л
    1.90
    or
    1.80
    er
    1.77
    е
    1.73
    ant
    1.68
    ennzeichnet
    1.67
    𝗲
    1.64
    द
    1.62
    고
    1.59
    POSITIVE LOGITS
     lineColorSpace
    1.82
     sigh
    1.77
     dzień
    1.75
    Bibliography
    1.74
    oleum
    1.70
     ina
    1.68
     onSuccess
    1.66
     тока
    1.64
    Thumbs
    1.63
     Notepad
    1.62
    Activations Density 0.008%

    No Known Activations