© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1106
    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
    datos
    0.58
     benutzt
    0.51
    ᅭ
    0.50
     rougeâtres
    0.50
     verwendet
    0.48
    pulsewidth
    0.46
     لینڈ
    0.46
     verwend
    0.46
    ़
    0.46
     もの
    0.45
    POSITIVE LOGITS
    ре
    0.53
    ньому
    0.50
    र
    0.48
    нього
    0.47
    ওলানা
    0.47
    𝐫
    0.46
    него
    0.46
    ۰۰
    0.46
    তা
    0.45
    𝐥
    0.44
    Activations Density 0.698%

    No Known Activations