© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to a football team, especially the New York Giants

    oai_token-act-pair · gemini-2.0-flash

    sports players

    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
    少
    -0.45
    rad
    -0.45
    pop
    -0.44
    Oh
    -0.43
     ولو
    -0.43
     pop
    -0.42
    il
    -0.42
     ob
    -0.41
    min
    -0.41
    ET
    -0.41
    POSITIVE LOGITS
     متعلقه
    1.07
    ⓧ
    1.05
     AssemblyCulture
    0.98
     kasarigan
    0.97
    SharedCtor
    0.96
    BibitemShut
    0.84
    principalColumn
    0.83
    ArgsConstructor
    0.82
    Geplaatst
    0.82
     isInitialized
    0.82
    Activations Density 3.127%

    No Known Activations