© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11640
    Prev
    Next
    INDEX
    Explanations

    statements about things happening in the future and phrases related to progress

    oai_token-act-pair · gemini-2.0-flash

    Rate/Pace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    UserScript
    -0.50
    idit
    -0.48
    ztő
    -0.47
     tiennent
    -0.46
     utom
    -0.45
     vasta
    -0.44
     parco
    -0.43
    ldc
    -0.43
    เป
    -0.42
     demostra
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.81
     Paglinawan
    0.77
     للاسماء
    0.74
     resourceCulture
    0.73
    enumii
    0.73
    
    0.66
     BoxDecoration
    0.65
    ReusableCell
    0.64
    tagHelperRunner
    0.62
    ChildScrollView
    0.61
    Activations Density 0.414%

    No Known Activations