© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11434
    Prev
    Next
    INDEX
    Explanations

    mentions of eyelashes and eyelash curlers, especially concerning their mechanical operation and cosmetic use.

    oai_token-act-pair · gemini-2.0-flash

    words related to cosmetic tools or devices

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

    Proper nouns

    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
    featureID
    -0.63
    WebVitals
    -0.63
     EconPapers
    -0.57
     AssemblyCulture
    -0.56
    dafx
    -0.51
    OrBuilder
    -0.51
    tetten
    -0.50
    RenderAtEndOf
    -0.50
     Petru
    -0.50
    accumulative
    -0.50
    POSITIVE LOGITS
    WebpackPlugin
    0.54
     ISTAT
    0.52
    usercontent
    0.52
     Superhosts
    0.52
    WindowConstants
    0.49
    jería
    0.48
     upper
    0.47
    تقاوى
    0.46
    Upper
    0.45
     SafeMath
    0.45
    Activations Density 1.283%

    No Known Activations