© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 11598
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to GitHub and Javascript frameworks

    oai_token-act-pair · gemini-2.0-flash

    issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    GOTREF
    -0.60
    Handlung
    -0.52
    //
    -0.51
    )++;
    -0.43
    atsen
    -0.43
    avía
    -0.42
     Journ
    -0.42
    lexikon
    -0.41
     affirmations
    -0.41
     Hora
    -0.41
    POSITIVE LOGITS
     resourceCulture
    0.96
    PreferredItem
    0.82
     issue
    0.81
     Issue
    0.80
     PR
    0.75
     Issues
    0.75
    issue
    0.74
     Pull
    0.73
     issues
    0.72
     pull
    0.71
    Activations Density 3.467%

    No Known Activations