© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    struct declarations in C code related to network programming, focusing on the `ip` member

    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
    ărilor
    -0.46
    ării
    -0.40
    Where
    -0.40
    lek
    -0.39
     gră
    -0.38
     pregă
    -0.36
     înal
    -0.33
    ‚¬
    -0.33
    SOUNDBITE
    -0.33
    Who
    -0.31
    POSITIVE LOGITS
    InjectAttribute
    0.86
    TagMode
    0.78
    djangoproject
    0.73
    thâu
    0.68
    XmlAccessType
    0.68
    Fordítás
    0.67
    Şi
    0.65
    ViewImports
    0.65
     consultato
    0.65
    Gambas
    0.65
    Activations Density 1.745%

    No Known Activations