Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10157
    Prev
    Next
    INDEX
    Explanations

    mentions of primary, secondary, or tertiary activity

    oai_token-act-pair · gemini-2.0-flash

    primary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.84
     समीक्षाओं
    -0.82
    webElementXpaths
    -0.75
    évaluateur
    -0.75
     تضيفلها
    -0.75
    сылкі
    -0.66
    AddTagHelper
    -0.66
    tagHelperRunner
    -0.62
    лтемелер
    -0.61
    thenReturn
    -0.60
    POSITIVE LOGITS
    ۪
    0.49
    Filmografie
    0.47
     till
    0.47
     circulation
    0.45
    glVertex
    0.43
     voud
    0.42
     row
    0.42
    jande
    0.40
    lccn
    0.40
    ौर
    0.39
    Activations Density 7.734%

    No Known Activations