© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5564
    Prev
    Next
    INDEX
    Explanations

    line breaks and quotation marks

    oai_token-act-pair · gemini-2.0-flash

    single quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    :+:
    -0.57
     []),
    -0.51
    viewDidLoad
    -0.51
    TouchListener
    -0.50
    AndEndTag
    -0.48
     {}'.
    -0.48
    +#+#
    -0.48
     nonUne
    -0.47
     дописавши
    -0.47
     beginnetje
    -0.46
    POSITIVE LOGITS
    apimachinery
    0.64
    lgari
    0.55
    DotNetBar
    0.54
     Xinjiang
    0.54
    steamcommunity
    0.53
     DOCUMENTS
    0.53
    ństwo
    0.53
    AsUp
    0.52
    ngOn
    0.52
     IUCN
    0.52
    Activations Density 0.225%

    No Known Activations