© 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. 5610
    Prev
    Next
    INDEX
    Explanations

    words and phrases from scientific papers about the physics of thermal particles

    oai_token-act-pair · gemini-2.0-flash

    Physics simulations

    np_max-act-logits · gemini-2.0-flash

    technical terms or keywords in scientific contexts

    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
    sens
    -0.46
    Odkazy
    -0.45
    KommentareTeilen
    -0.44
     relâche
    -0.43
     resourceCulture
    -0.43
    Bibliographie
    -0.42
     appelez
    -0.42
    itinéraire
    -0.41
    QMetaType
    -0.41
     שוליים
    -0.40
    POSITIVE LOGITS
    #+#
    0.75
    UnsafeEnabled
    0.65
    RectangleBorder
    0.63
    раздо
    0.61
    TProtocol
    0.59
     gewor
    0.57
    enumii
    0.57
    InputBorder
    0.57
     سكانية
    0.57
     jsPsych
    0.56
    Activations Density 4.078%

    No Known Activations