© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13049
    Prev
    Next
    INDEX
    Explanations

    athletes' names

    oai_token-act-pair · gemini-2.0-flash

    Sports team players and performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     BoxFit
    -0.66
    CloseOperation
    -0.64
    dyž
    -0.57
     dumne
    -0.56
    psack
    -0.54
    itoneum
    -0.54
     CWE
    -0.52
     CreateTagHelper
    -0.51
    Bronnen
    -0.50
    thalene
    -0.49
    POSITIVE LOGITS
    <bos>
    0.78
    yntaxException
    0.60
     Wikimedijinoj
    0.58
    riezmann
    0.54
    principalTable
    0.52
     nonatomic
    0.52
    CodeAttribute
    0.51
    ंदीखरीदारी
    0.51
    umab
    0.49
    َع
    0.49
    Activations Density 0.357%

    No Known Activations