© 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. 2268
    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
    ঙ্গার
    2.72
    ็จ
    2.64
     supernatant
    2.51
     supernatants
    2.48
    ̀
    2.48
    llä
    2.47
    ycin
    2.46
     adjunction
    2.38
    ᾷ
    2.33
     strani
    2.28
    POSITIVE LOGITS
    n
    2.73
    ુ
    2.62
    est
    2.59
    é
    2.50
     possibility
    2.48
    emiz
    2.47
    ме
    2.45
    رض
    2.41
     steepest
    2.37
     해당하는
    2.36
    Activations Density 0.041%

    No Known Activations