© 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. 6167
    Prev
    Next
    INDEX
    Explanations

    a blend of positive sentiment, mild emphasis, and a touch of formality, often related to legal or bureaucratic processes.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and information

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

    Business/advertising content

    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
    AddTagHelper
    -0.65
     ویکی‌پدی
    -0.65
     ویکی‌پدیا
    -0.64
     שוליים
    -0.63
     supérieurs
    -0.61
    ificantly
    -0.60
    bootstrapcdn
    -0.59
    обходимо
    -0.58
    tagHelperRunner
    -0.56
     Theſe
    -0.54
    POSITIVE LOGITS
     info
    0.60
     picked
    0.60
    Etimología
    0.60
    oredCriteria
    0.57
     chances
    0.57
     inside
    0.57
     comfy
    0.57
     pick
    0.56
    ViewFeatures
    0.55
     kind
    0.54
    Activations Density 2.394%

    No Known Activations