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. 6949
    Prev
    Next
    INDEX
    Explanations

    HTML div elements with class and id attributes, often associated with form elements and bootstrap styling.

    oai_token-act-pair · gemini-2.0-flash

    class

    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
    fony
    -0.52
     झ
    -0.49
    verhalten
    -0.48
    detectChanges
    -0.48
     marks
    -0.44
    TRAILING
    -0.44
    ValueGenerated
    -0.43
     gesloten
    -0.43
    numberOfLines
    -0.43
    Shh
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.68
    verso
    0.64
     ivelany
    0.63
    بوابة
    0.61
    =?";
    0.59
     Biôgrafia
    0.57
    NUMX
    0.56
     utafitiHapana
    0.56
     muualla
    0.55
    jmniej
    0.54
    Activations Density 0.061%

    No Known Activations