© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7614
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers

    oai_token-act-pair · gemini-2.0-flash

    programming or markup elements

    np_token-act-pair-logits · gpt-4o-mini

    technical documents, papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     thousand
    -0.65
     thousands
    -0.63
     THOUS
    -0.56
     Thousands
    -0.52
     milliers
    -0.49
    Thousands
    -0.48
     millions
    -0.48
    thousands
    -0.46
     hundred
    -0.45
     hund
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.80
    NewUrlParser
    0.78
     समीक्षाएं
    0.73
    WriteTagHelper
    0.72
    ViewFeatures
    0.72
    السكان
    0.71
    InjectAttribute
    0.71
    didSet
    0.66
    WebVitals
    0.65
    FormTagHelper
    0.65
    Activations Density 5.255%

    No Known Activations