© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    words in context, academia, argumentitive writing

    oai_token-act-pair · gemini-2.0-flash

    debate/argument

    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
    ArgsConstructor
    -0.94
    SequentialGroup
    -0.79
     >=",
    -0.67
     kasarigan
    -0.66
    AddTagHelper
    -0.66
    Lycka
    -0.64
    libft
    -0.63
     houſe
    -0.63
     stiefel
    -0.62
    ParallelGroup
    -0.61
    POSITIVE LOGITS
    <bos>
    0.73
    XmlAccessType
    0.50
    SerializedName
    0.48
     route
    0.44
     escritores
    0.43
    EXTERN
    0.41
     utom
    0.39
     dial
    0.39
     dàng
    0.39
     gul
    0.38
    Activations Density 39.463%

    No Known Activations