© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    words and phrases appearing in news reports, especially those that include datelines and direct quotes.

    oai_token-act-pair · gemini-2.0-flash

    reporting news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    الحياه
    -0.52
    laka
    -0.50
    +#+#
    -0.47
    findpost
    -0.46
     esqueleto
    -0.46
    Зе
    -0.44
    LabelTagHelper
    -0.44
     dono
    -0.43
    パーク
    -0.42
     clairement
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.73
    protoc
    0.72
    GEBURTSDATUM
    0.72
    IntoConstraints
    0.65
    ruptedException
    0.63
    PerformLayout
    0.61
    UIControlState
    0.60
    InstanceState
    0.57
    awtextra
    0.57
    Tome
    0.57
    Activations Density 2.748%

    No Known Activations