© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1317
    Prev
    Next
    INDEX
    Explanations

    percentages related to numerical values and measurement

    oai_token-act-pair · gemini-2.0-flash

    Percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    
    -0.82
    homonymie
    -0.62
    GraphicsUnit
    -0.59
    UrlResolution
    -0.59
    lankton
    -0.58
     \%)$
    -0.57
     "..\..\..\
    -0.57
    jsonwebtoken
    -0.57
    PreExecute
    -0.54
    %=
    -0.53
    POSITIVE LOGITS
    makeConstraints
    0.58
    parsedMessage
    0.50
     artificiales
    0.46
     tecniche
    0.45
     asal
    0.44
     الحره
    0.43
    methods
    0.43
    کید
    0.43
    atitis
    0.43
    {
    0.43
    Activations Density 8.527%

    No Known Activations