Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5548
    Prev
    Next
    INDEX
    Explanations

    words and acronyms related to signal frequency and transmission

    oai_token-act-pair · gemini-2.0-flash

    terms related to cycles and frequency

    np_token-act-pair-logits · gpt-4o-mini

    Computer processing frequencies

    np_max-act-logits · gemini-2.0-flash
    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
     >=",
    -0.66
     дописавши
    -0.66
     AppModule
    -0.59
    مصادر
    -0.56
    complexContent
    -0.54
     <=",
    -0.53
     NSCoder
    -0.52
     للاسماء
    -0.52
    rungsseite
    -0.52
     km
    -0.51
    POSITIVE LOGITS
     cycles
    0.83
     protoimpl
    0.79
     cycle
    0.76
    cycle
    0.70
     her
    0.70
    cycles
    0.69
     Cycles
    0.69
     Hert
    0.65
     ciclos
    0.64
    ヘル
    0.63
    Activations Density 2.539%

    No Known Activations