© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    code syntax such as semicolons, parentheses, curly brackets, and colons

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    abestanden
    -0.68
     समीक्षक
    -0.65
    antMatchers
    -0.65
     تعدى
    -0.60
     AssemblyTitle
    -0.60
    Geplaatst
    -0.60
    WebElementEntity
    -0.58
    ukone
    -0.57
     démocr
    -0.57
     nakalista
    -0.57
    POSITIVE LOGITS
     number
    0.54
     Number
    0.49
     Wedge
    0.44
     Legendre
    0.42
     Charlemagne
    0.42
     ibid
    0.40
     Cow
    0.40
     Alcohol
    0.40
     pylint
    0.40
     furthermore
    0.39
    Activations Density 4.904%

    No Known Activations