© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3097
    Prev
    Next
    INDEX
    Explanations

    the phrase "check out" referring to visiting a website or publication

    oai_token-act-pair · gemini-2.0-flash

    check

    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
     trademark
    -0.80
    trade
    -0.78
     trade
    -0.74
     trademarks
    -0.70
    Trade
    -0.69
     Trade
    -0.68
    StoryboardSegue
    -0.65
    Trademark
    -0.63
     registered
    -0.62
     فريبيس
    -0.62
    POSITIVE LOGITS
     out
    1.30
    out
    0.92
    Out
    0.71
     Out
    0.69
     autorytatywna
    0.69
    outs
    0.66
     OUT
    0.65
     تانيه
    0.63
    EOUT
    0.62
     outs
    0.59
    Activations Density 0.496%

    No Known Activations