© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9017
    Prev
    Next
    INDEX
    Explanations

    hedging language like quotes, potentiality and conditionality

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -0.59
    richlet
    -0.52
    zins
    -0.49
    PyTuple
    -0.48
    CURLOPT
    -0.47
    WithString
    -0.47
    ,:]
    -0.47
    setOnAction
    -0.44
    gias
    -0.44
    RegistryLite
    -0.43
    POSITIVE LOGITS
     preſent
    0.81
     Anſ
    0.80
     Theſe
    0.79
     purpoſe
    0.79
     whoſe
    0.78
     uſe
    0.77
    ſelf
    0.76
     autorytatywna
    0.75
     Diſ
    0.73
    évaluateur
    0.73
    Activations Density 9.696%

    No Known Activations