© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10516
    Prev
    Next
    INDEX
    Explanations

    code-related terms like variable names, function calls, and data types

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.09
    DockStyle
    -0.73
    awtextra
    -0.68
    はじめに
    -0.66
    cshtml
    -0.66
    StoryboardSegue
    -0.65
    onAttach
    -0.61
    omitempty
    -0.60
    EndContext
    -0.60
    endregion
    -0.60
    POSITIVE LOGITS
    ;#
    0.64
    ()][
    0.58
    zzar
    0.57
    
    0.56
    ########.
    0.56
    Kund
    0.55
    JPL
    0.53
     shelters
    0.53
     antropo
    0.52
     Waits
    0.52
    Activations Density 1.427%

    No Known Activations