© 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. 12441
    Prev
    Next
    INDEX
    Explanations

    words associated with analysis and summarization, especially in the contexts of business and technical subjects like programming, blogs, and finance.

    oai_token-act-pair · gemini-2.0-flash

    blog posts and errors

    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
     تضيفلها
    -0.80
     propOrder
    -0.78
    sizeCache
    -0.73
    RegistryLite
    -0.69
    httphttps
    -0.69
    Gambas
    -0.67
    IVEREF
    -0.66
    +:+
    -0.66
    ьаж
    -0.66
    BeginContext
    -0.64
    POSITIVE LOGITS
    Rgds
    0.49
    ortic
    0.49
     
    0.47
     propi
    0.47
    wantErr
    0.47
    triangleq
    0.45
     -
    0.45
     team
    0.44
     mxArray
    0.44
     виправивши
    0.44
    Activations Density 2.032%

    No Known Activations