© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14977
    Prev
    Next
    INDEX
    Explanations

    mentions of the US national soccer team

    oai_token-act-pair · gemini-2.0-flash

    international sports teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Enllaces
    -0.63
     resourceCulture
    -0.55
    ground
    -0.52
     سكانية
    -0.51
     AssemblyCulture
    -0.51
    Ground
    -0.51
     subido
    -0.50
    脚注の使い方
    -0.50
    microb
    -0.50
    tagHelperRunner
    -0.49
    POSITIVE LOGITS
    StructEnd
    0.56
    migrationBuilder
    0.54
     Bundesliga
    0.50
    FXML
    0.49
    xhtml
    0.47
     Fußballspieler
    0.47
     NHL
    0.47
     Czech
    0.46
    IVEREF
    0.46
    ARGB
    0.46
    Activations Density 3.399%

    No Known Activations