© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 872
    Prev
    Next
    INDEX
    Explanations

    capitalized words, especially proper nouns, and words related to web design

    oai_token-act-pair · gemini-2.0-flash

    CMSWire and file paths

    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
     neutral
    -0.50
     literature
    -0.48
     Wire
    -0.47
     Literature
    -0.46
    зий
    -0.46
    tein
    -0.45
     met
    -0.44
     ModelExpression
    -0.44
     Ganz
    -0.44
     campus
    -0.40
    POSITIVE LOGITS
    oredCriteria
    0.87
     فريبيس
    0.70
    endphp
    0.69
     صوتيه
    0.69
     Jefus
    0.69
    Diweddarwch
    0.69
    Slf
    0.66
    Rhestr
    0.65
    SharedCtor
    0.62
    iconque
    0.61
    Activations Density 12.459%

    No Known Activations