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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 517
    Prev
    Next
    INDEX
    Explanations

    code snippets involving parentheses and curly braces

    oai_token-act-pair · gemini-2.0-flash

    Code/system configuration

    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
    sizeCache
    -0.76
    Parcelize
    -0.75
    :+:
    -0.75
    KEYCODE
    -0.75
     }{@
    -0.71
     AssemblyCulture
    -0.71
    ImageContext
    -0.69
     snippetHide
    -0.68
     <=",
    -0.67
    Erreferentziak
    -0.66
    POSITIVE LOGITS
     nargin
    0.49
    Décès
    0.46
    енера
    0.41
     plass
    0.41
    cody
    0.40
    scales
    0.40
    PostId
    0.40
     away
    0.40
    ندر
    0.40
     scales
    0.39
    Activations Density 2.649%

    No Known Activations