© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1259
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     transfieras
    -0.75
    rawDesc
    -0.73
     ―――――
    -0.73
     مرئيه
    -0.73
     ujednoznacz
    -0.72
    WebVitals
    -0.72
    IBarButtonItem
    -0.72
     timeval
    -0.71
    Diwedd
    -0.71
    NgModule
    -0.70
    POSITIVE LOGITS
     verfügt
    0.42
     minh
    0.39
     pudo
    0.39
     volantes
    0.39
    encodeWith
    0.38
     elér
    0.38
    mack
    0.37
    }^{+\
    0.37
     mög
    0.37
     almofada
    0.37
    Activations Density 3.370%

    No Known Activations