© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13014
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to news and reporting, especially direct quotes and source attributions

    oai_token-act-pair · gemini-2.0-flash

    News agencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     éto
    -0.58
    createServer
    -0.51
    وصلات
    -0.50
     насељу
    -0.47
    openConnection
    -0.46
    yatı
    -0.46
     muualla
    -0.45
    \{\\
    -0.45
    didSet
    -0.44
     população
    -0.43
    POSITIVE LOGITS
     Reuters
    0.69
     AFP
    0.68
    AFP
    0.67
     agency
    0.63
    Reuters
    0.60
    ристання
    0.59
     agencies
    0.59
    UTERS
    0.57
    Agence
    0.56
     news
    0.55
    Activations Density 0.746%

    No Known Activations