© 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. 251
    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
    ة
    3.43
    berly
    2.72
    নের
    2.54
    ций
    2.46
    transfected
    2.35
    flexible
    2.30
    whale
    2.26
     sympathetic
    2.26
     antifreeze
    2.25
    nesota
    2.24
    POSITIVE LOGITS
    р
    3.08
    ный
    2.52
    m
    2.38
    З
    2.35
     बना
    2.29
    П
    2.29
    по
    2.26
    လ်
    2.25
    वानिव
    2.12
     voici
    2.12
    Activations Density 0.013%

    No Known Activations