© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4844
    Prev
    Next
    INDEX
    Explanations

    opening curly braces and parentheses in code

    oai_token-act-pair · gemini-2.0-flash

    right parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    出版年
    -0.54
    يميديا
    -0.54
    octanol
    -0.51
    idalgo
    -0.50
    Firm
    -0.49
    homonymie
    -0.49
     Fis
    -0.48
     Firm
    -0.48
    rinfo
    -0.48
    +:+
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.69
    ArrowToggle
    0.63
    windowFixed
    0.56
     /\.
    0.56
    UpInside
    0.52
     Италијани
    0.51
    EndGlobalSection
    0.50
     estimators
    0.49
    UnusedPrivate
    0.49
     Disqus
    0.49
    Activations Density 0.650%

    No Known Activations