© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    quotation marks, the words "word" or "term", and sometimes the infinitive form of the word to.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    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
     nahilalakip
    -0.57
    autoreleasepool
    -0.56
    \"></
    -0.54
    AsUp
    -0.54
    RegressionTest
    -0.53
    errHandler
    -0.49
     }</
    -0.49
    contentLoaded
    -0.48
    '},
    -0.48
    principalTable
    -0.47
    POSITIVE LOGITS
     Belt
    0.55
     résine
    0.55
     montrant
    0.52
     ventre
    0.52
     acte
    0.52
    ActionEvent
    0.51
    ̍t
    0.51
     hinzugefügt
    0.50
     poitrine
    0.50
    misión
    0.50
    Activations Density 4.137%

    No Known Activations