© 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. 2159
    Prev
    Next
    INDEX
    Explanations

    words that are used in scientific arguments to provide support for a hypothesis

    oai_token-act-pair · gemini-2.0-flash

    that

    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
     חיצוניים
    -0.97
     שוליים
    -0.81
     themſelves
    -0.77
    XmlAccessorType
    -0.74
     reaſon
    -0.73
     Normdatei
    -0.71
    DeleteBehavior
    -0.71
     Theſe
    -0.69
     ſever
    -0.69
    KommentareTeilen
    -0.69
    POSITIVE LOGITS
     betweenstory
    0.62
     an
    0.56
     higher
    0.54
     using
    0.53
    +:+
    0.52
     recognizing
    0.52
     cra
    0.51
     committing
    0.51
     our
    0.50
     taking
    0.50
    Activations Density 3.126%

    No Known Activations