© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and associated attributes

    oai_token-act-pair · gemini-2.0-flash

    form inputs

    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
     שוליים
    -0.54
    τοι
    -0.49
    omiast
    -0.48
    myModal
    -0.47
    Filmografia
    -0.43
     offside
    -0.43
    arashtra
    -0.42
    hadiran
    -0.42
    olk
    -0.42
    vací
    -0.42
    POSITIVE LOGITS
    WithIOException
    0.70
    كويكب
    0.68
    ValueStyle
    0.66
     htons
    0.63
    uxxxx
    0.62
    kháu
    0.60
    RegressionTest
    0.59
    Coordonnées
    0.58
    StringCopy
    0.56
    addCriterion
    0.55
    Activations Density 3.143%

    No Known Activations