© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2964
    Prev
    Next
    INDEX
    Explanations

    numbers and decimals

    oai_token-act-pair · gemini-2.0-flash

    number 5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Seventh
    -0.92
     seventh
    -0.89
    InjectAttribute
    -0.88
     Seven
    -0.87
     resourceCulture
    -0.83
    GEBURTSDATUM
    -0.80
    Seventh
    -0.80
    ValueStyle
    -0.79
    SequentialGroup
    -0.79
     seven
    -0.76
    POSITIVE LOGITS
    5
    0.77
    fifths
    0.66
     five
    0.65
    4
    0.64
    ５
    0.58
     fifth
    0.58
     Five
    0.58
     cinque
    0.57
     cinco
    0.56
     FIVE
    0.56
    Activations Density 2.162%

    No Known Activations