© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6242
    Prev
    Next
    INDEX
    Explanations

    MATLAB code syntax for image processing

    oai_token-act-pair · gemini-2.0-flash

    code/data

    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
     (
    -0.56
     perd
    -0.50
    (
    -0.47
     spot
    -0.47
     safe
    -0.47
     official
    -0.45
     functionally
    -0.45
    자가
    -0.44
     $(
    -0.43
     sis
    -0.43
    POSITIVE LOGITS
    UserScript
    0.72
     cherchés
    0.70
    modb
    0.65
    Koordinaten
    0.64
    InputTagHelper
    0.63
    mappedBy
    0.62
    rawDesc
    0.62
    AccessorTable
    0.62
    addPreferredGap
    0.60
    ELTS
    0.60
    Activations Density 1.389%

    No Known Activations