© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2506
    Prev
    Next
    INDEX
    Explanations

    various tables of numbers and codes with headers, especially related to some kind of experiment

    oai_token-act-pair · gemini-2.0-flash

    Data and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    SupportActionBar
    -0.54
    FTFY
    -0.50
     Reverso
    -0.50
    setAddress
    -0.49
    digheden
    -0.47
    Uwagi
    -0.46
     Cyrus
    -0.45
     Schmer
    -0.45
    Poznám
    -0.45
    izoen
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.87
    CloseOperation
    0.73
    VIAF
    0.69
    parsedMessage
    0.63
    OrNil
    0.57
    Hochspringen
    0.57
    webElementGuid
    0.57
    IBOutlet
    0.57
    bootstrapcdn
    0.57
     }</
    0.57
    Activations Density 1.816%

    No Known Activations