© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15575
    Prev
    Next
    INDEX
    Explanations

    adverbs

    oai_token-act-pair · gemini-2.0-flash

    so/very

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.79
    GEBURTSDATUM
    -0.61
    setVerticalGroup
    -0.59
    انيف
    -0.59
     endwhile
    -0.57
    yntaxException
    -0.57
    cshtml
    -0.56
    most
    -0.56
     precisione
    -0.55
     rapides
    -0.54
    POSITIVE LOGITS
     متعلقه
    0.71
     fully
    0.62
     recently
    0.59
     completely
    0.57
    ]--;
    0.57
     explicitly
    0.53
     Completely
    0.52
     blatantly
    0.52
     nearly
    0.52
     openly
    0.52
    Activations Density 1.686%

    No Known Activations