© 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. 1039
    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
    À
    0.37
    espère
    0.32
    Sementara
    0.30
    Á
    0.30
    ließ
    0.30
     Majesty
    0.30
    Excerpt
    0.30
    женности
    0.30
     Mitglied
    0.30
    Má
    0.30
    POSITIVE LOGITS
    ′,
    0.36
    oretically
    0.35
    ️⃣
    0.33
     unquestion
    0.33
    ूहिक
    0.33
    at
    0.30
    ⃣
    0.30
     LDL
    0.30
    theless
    0.29
    ″
    0.29
    Activations Density 0.756%

    No Known Activations