© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14691
    Prev
    Next
    INDEX
    Explanations

    the word "keep" as well as inflections of it

    oai_token-act-pair · gemini-2.0-flash

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    LookAnd
    -0.92
     Huguen
    -0.80
     تضيفلها
    -0.79
     Reſ
    -0.75
     Beſ
    -0.74
     Theſe
    -0.74
     iſt
    -0.74
     Vikipedi
    -0.72
    RectangleBorder
    -0.71
     ―――――
    -0.71
    POSITIVE LOGITS
    <bos>
    0.59
    nál
    0.47
     possession
    0.47
     "
    0.46
     er
    0.46
     bag
    0.46
    henswürdigkeiten
    0.44
    id
    0.42
     At
    0.42
    partiet
    0.42
    Activations Density 1.171%

    No Known Activations