© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7548
    Prev
    Next
    INDEX
    Explanations

    words like "generally", "typical", and "example", indicating broad statements or common occurrences.

    oai_token-act-pair · gemini-2.0-flash

    generally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    wnież
    -1.05
     CreateTagHelper
    -1.02
    ardless
    -0.83
    IBarButtonItem
    -0.78
    mybatisplus
    -0.74
     actionPerformed
    -0.71
    CreateMap
    -0.71
    PerformLayout
    -0.71
    rillation
    -0.70
    ]--;
    -0.70
    POSITIVE LOGITS
    <bos>
    0.79
    missione
    0.50
     zve
    0.45
    lan
    0.44
     General
    0.41
    idah
    0.40
    mid
    0.40
    WinForms
    0.40
     mid
    0.39
    rijf
    0.39
    Activations Density 2.262%

    No Known Activations