© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1977
    Prev
    Next
    INDEX
    Explanations

    descriptions of things being made from component parts

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Datuak
    -0.70
    Personensuche
    -0.65
     ModelExpression
    -0.62
    expandindo
    -0.57
    webElement
    -0.57
    kháu
    -0.55
    imanapun
    -0.54
    onViewCreated
    -0.54
    Rüyada
    -0.53
    existsSync
    -0.52
    POSITIVE LOGITS
     from
    1.49
     out
    1.13
     dari
    1.11
     из
    1.10
    from
    1.10
    จาก
    1.04
     FROM
    1.00
     outta
    0.98
     From
    0.98
     από
    0.94
    Activations Density 1.387%

    No Known Activations