© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5609
    Prev
    Next
    INDEX
    Explanations

    terms related to computer connectivity and storage, with a strong emphasis on USB

    oai_token-act-pair · gemini-2.0-flash

    USB

    np_max-act-logits · gemini-2.0-flash

    prefixes or fragments of proper nouns

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ویکی‌پدی
    -0.79
    hasMoreElements
    -0.79
     defaultstate
    -0.76
    IContainer
    -0.75
    ChildScrollView
    -0.75
    TintMode
    -0.74
    はじめに
    -0.69
    Geplaatst
    -0.69
    lapsingToolbar
    -0.69
    Jeografia
    -0.68
    POSITIVE LOGITS
    eci
    0.47
     jel
    0.45
    כ
    0.44
     du
    0.43
    onna
    0.43
    muo
    0.42
    rowski
    0.42
     Times
    0.40
     c
    0.40
    essy
    0.39
    Activations Density 0.740%

    No Known Activations