© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13850
    Prev
    Next
    INDEX
    Explanations

    examples or mentions of computer code and programming languages

    oai_token-act-pair · gemini-2.0-flash

    file formats or extensions

    np_token-act-pair-logits · gpt-4o-mini

    detects file extensions and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Décès
    -0.57
     Drapeau
    -0.52
     arşivlendi
    -0.51
     Mountain
    -0.51
    igshid
    -0.49
     cherchés
    -0.49
    ždy
    -0.49
    ///</
    -0.47
    🇶
    -0.47
     mountain
    -0.46
    POSITIVE LOGITS
    PMailer
    0.66
    PYX
    0.54
     bat
    0.54
    URLException
    0.54
    docx
    0.52
    bat
    0.52
    Pdf
    0.50
     iNdEx
    0.50
    AddHtmlAttribute
    0.50
     Exped
    0.49
    Activations Density 2.740%

    No Known Activations