© 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. 9049
    Prev
    Next
    INDEX
    Explanations

    code snippets or language and their attributes, such as commands, arguments, and properties

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     Theſe
    -0.91
     purpoſe
    -0.88
     Monfieur
    -0.83
    OGND
    -0.79
     ModelExpression
    -0.79
     pleaſure
    -0.78
    AndEndTag
    -0.77
    Datuak
    -0.77
     onCancelled
    -0.77
    enumi
    -0.76
    POSITIVE LOGITS
    ='')
    0.57
     "
    0.55
    ="#">
    0.49
    ="")
    0.49
     '
    0.46
    ,
    0.42
    ="/">
    0.41
    ="{
    0.41
    ="",
    0.40
    ='
    0.40
    Activations Density 6.830%

    No Known Activations