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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6971
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and percentages

    oai_token-act-pair · gemini-2.0-flash

    Diverse data, code, math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     autorytatywna
    -0.77
    getRuntime
    -0.60
     Wikimedijinoj
    -0.59
    afficheront
    -0.59
    ViewFeatures
    -0.56
    OGND
    -0.55
     Enfin
    -0.54
    verifyException
    -0.54
     архивлан
    -0.52
    twimg
    -0.52
    POSITIVE LOGITS
     unknownFields
    0.56
    Economía
    0.50
    stdafx
    0.48
     Zorn
    0.46
    gül
    0.46
    âce
    0.45
    globo
    0.45
    ähne
    0.44
    hésite
    0.43
    ⓘ
    0.43
    Activations Density 3.056%

    No Known Activations