© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3350
    Prev
    Next
    INDEX
    Explanations

    locations of enumerated lists, especially in legal or scientific documents

    oai_token-act-pair · gemini-2.0-flash

    enumerations

    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
    StoryboardSegue
    -1.01
    
    -0.73
    oa̍t
    -0.71
     pinulongan
    -0.70
    endmodule
    -0.69
     houſe
    -0.69
    Datuak
    -0.69
    <bos>
    -0.68
     myſelf
    -0.68
     perfons
    -0.67
    POSITIVE LOGITS
    paro
    0.50
    True
    0.48
     True
    0.47
    >-->
    0.47
     par
    0.46
     Par
    0.45
     true
    0.45
     mut
    0.45
    annas
    0.44
    üse
    0.43
    Activations Density 8.933%

    No Known Activations