© 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. 5747
    Prev
    Next
    INDEX
    Explanations

    monetary figures or numeric values

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     dAtA
    -0.56
    <bos>
    -0.54
    waitKey
    -0.51
     Theſe
    -0.48
    enderror
    -0.47
    interface
    -0.47
     tendances
    -0.46
     生命周期
    -0.45
    end
    -0.44
     pytest
    -0.43
    POSITIVE LOGITS
     banks
    0.66
     blocks
    0.61
    Datuak
    0.60
     acorns
    0.60
     households
    0.60
     francs
    0.60
    TextBoxColumn
    0.60
     horses
    0.60
     Himo
    0.60
     euros
    0.59
    Activations Density 4.743%

    No Known Activations