© 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. 8824
    Prev
    Next
    INDEX
    Explanations

    code and code-related terminology

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    <unused61>
    -0.33
    <unused60>
    -0.30
    <unused63>
    -0.29
    追
    -0.28
    <unused62>
    -0.28
     βά
    -0.26
     tä
    -0.24
    日
    -0.23
    願
    -0.21
    lové
    -0.20
    POSITIVE LOGITS
     Theſe
    1.34
     myſelf
    1.33
     Monfieur
    1.30
     pleaſure
    1.30
     becauſe
    1.27
     houſe
    1.27
    <unused28>
    1.26
    <unused41>
    1.26
    <unused17>
    1.26
    <unused7>
    1.26
    Activations Density 12.305%

    No Known Activations