© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 617
    Prev
    Next
    INDEX
    Explanations

    words, especially acronyms, related to scientific measurement and reporting such as used in medical papers.

    oai_token-act-pair · 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
     temperature
    -1.84
     cold
    -1.73
     Temperature
    -1.66
    cold
    -1.65
    Temperature
    -1.63
    temperature
    -1.60
     temperatures
    -1.59
    Cold
    -1.59
     Cold
    -1.57
     COLD
    -1.53
    POSITIVE LOGITS
    lark
    0.54
     Hogarth
    0.50
    ltä
    0.50
    orla
    0.49
     Pooja
    0.49
     Undeclared
    0.48
     Amiens
    0.47
    оти
    0.47
     فريبيس
    0.47
    cjon
    0.46
    Activations Density 1.970%

    No Known Activations