© 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
    2. Gemma-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 292
    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
    кий
    1.56
    こ
    1.49
     teaspoons
    1.35
     inadequacy
    1.35
     inadequate
    1.33
     PACS
    1.32
     inefficiency
    1.31
     impossible
    1.31
    rivers
    1.28
     thinning
    1.28
    POSITIVE LOGITS
    ς
    1.94
    ের
    1.94
    있는
    1.76
    ные
    1.69
    م
    1.66
    сибо
    1.63
    AN
    1.62
    elor
    1.61
    辦法
    1.55
    posites
    1.55
    Activations Density 0.288%

    No Known Activations