© 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. 7599
    Prev
    Next
    INDEX
    Explanations

    strings of numbers including the number zero

    oai_token-act-pair · gemini-2.0-flash

    non-English words or names

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

    0

    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
    fjspx
    -0.75
    PYX
    -0.56
    propTypes
    -0.54
     ujednoznacz
    -0.52
     possible
    -0.52
     ۰
    -0.50
    ۰۱
    -0.50
    raszamy
    -0.49
    TableModel
    -0.49
    0
    -0.49
    POSITIVE LOGITS
    wnicy
    0.54
     kasarigan
    0.54
    ppsala
    0.50
    Semoga
    0.49
    hopped
    0.48
    قایناق‌لار
    0.48
    annica
    0.47
     незавершена
    0.47
     arada
    0.46
     مرئيه
    0.45
    Activations Density 0.455%

    No Known Activations