© 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. 12039
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration files, particularly those involving conditional statements and boolean values.

    oai_token-act-pair · gemini-2.0-flash

    yes

    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
     <",
    -0.65
    MLLoader
    -0.61
    rungsseite
    -0.58
     Савезне
    -0.57
    AutoScaleMode
    -0.57
    URLException
    -0.56
    omiast
    -0.55
     resourceCulture
    -0.52
    Ranks
    -0.52
    endpush
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.54
     يتيمه
    0.48
    vande
    0.47
    ävän
    0.47
    setopt
    0.46
    DotNetBar
    0.46
     Funktion
    0.46
    ENEFITS
    0.45
    جمعیت
    0.45
     true
    0.45
    Activations Density 0.792%

    No Known Activations