© 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. 9691
    Prev
    Next
    INDEX
    Explanations

    non-English code snippets and tags in different languages, including HTML, Javascript, and French

    oai_token-act-pair · gemini-2.0-flash

    references to recognition and support structures

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

    code, foreign language

    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
    Personendaten
    -0.88
     nahilalakip
    -0.88
    Demografie
    -0.83
     estekak
    -0.80
     betweenstory
    -0.77
    strix
    -0.73
    AutoresizingMask
    -0.72
    قایناقلار
    -0.72
    :+:
    -0.71
    قایناق‌لار
    -0.71
    POSITIVE LOGITS
     exercise
    0.42
     Wikimedijinoj
    0.36
     he
    0.35
    ono
    0.35
    head
    0.35
     she
    0.34
     cit
    0.34
    exercise
    0.34
     samostat
    0.34
     gambe
    0.33
    Activations Density 2.279%

    No Known Activations