© 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. 3521
    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
    t
    2.50
    ت
    1.99
    т
    1.96
    تس
    1.92
    tog
    1.79
    tze
    1.75
    larda
    1.73
    تون
    1.71
    ဲ
    1.70
    tls
    1.70
    POSITIVE LOGITS
    ある
    1.81
    টির
    1.60
    की
    1.56
    кий
    1.51
    volving
    1.48
    grande
    1.46
    poison
    1.46
     sputter
    1.45
    HYDRO
    1.45
    ']])
    1.45
    Activations Density 0.011%

    No Known Activations