© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12694
    Prev
    Next
    INDEX
    Explanations

    the word "extra" and words suggesting add-ons or features

    oai_token-act-pair · gemini-2.0-flash

    extra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     purpoſe
    -0.68
     supérieurs
    -0.63
    AuthGuard
    -0.63
    Приятного
    -0.62
     nécessairement
    -0.61
    ^(@)
    -0.60
     klara
    -0.60
     exécu
    -0.60
    anguard
    -0.59
    theilung
    -0.59
    POSITIVE LOGITS
    CreateModel
    0.56
     متعلقه
    0.54
     ga
    0.54
    <bos>
    0.53
     needed
    0.53
    s
    0.52
     required
    0.52
    kw
    0.52
    then
    0.52
     then
    0.52
    Activations Density 0.388%

    No Known Activations