© 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. 16324
    Prev
    Next
    INDEX
    Explanations

    regular expression syntax

    oai_token-act-pair · gemini-2.0-flash

    Variations of "a"

    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
    BeginContext
    -0.92
    出版年
    -0.80
     ProtoMessage
    -0.78
    bootstrapcdn
    -0.77
    RenderAtEndOf
    -0.76
     AssemblyProduct
    -0.76
    artifactId
    -0.75
    saraba
    -0.75
    Portale
    -0.74
    Portail
    -0.73
    POSITIVE LOGITS
    A
    0.68
    a
    0.60
     A
    0.56
    а
    0.48
    Ａ
    0.44
     a
    0.43
    А
    0.43
    aing
    0.40
    aA
    0.39
     А
    0.39
    Activations Density 1.152%

    No Known Activations