© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15328
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with computing tasks or electronics

    oai_token-act-pair · gemini-2.0-flash

    Slashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     '\\;'
    -0.95
    DeleteBehavior
    -0.91
    ngdoc
    -0.90
     Мексичка
    -0.86
     ་་
    -0.85
     NSCoder
    -0.83
    abetes
    -0.82
    IUrlHelper
    -0.82
     resourceCulture
    -0.81
     مشين
    -0.79
    POSITIVE LOGITS
    /
    3.16
     /
    2.47
    ／
    1.84
    -/
    1.63
    ./
    1.56
    /(
    1.49
    /\
    1.48
    /"
    1.44
    /.
    1.41
    ()/
    1.39
    Activations Density 6.167%

    No Known Activations