© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    personal or subjective opinions of the author, especially when discussing past experiences and future expectations or intentions.

    oai_token-act-pair · gemini-2.0-flash

    article

    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
    Према
    -0.49
     LCCN
    -0.47
    LabelTagHelper
    -0.46
    وفاته
    -0.46
    ávání
    -0.46
    ipun
    -0.45
    plom
    -0.44
    /******/
    -0.44
     لينك
    -0.43
    hoeddwyd
    -0.43
    POSITIVE LOGITS
     article
    1.72
     articles
    1.56
    article
    1.31
     Article
    1.29
     Articles
    1.25
    Article
    1.21
    articles
    1.17
     artikel
    1.16
    Articles
    1.16
     ARTICLE
    1.14
    Activations Density 2.284%

    No Known Activations