© 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. 6141
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific calculations or notations

    oai_token-act-pair · gemini-2.0-flash

    programming or computational terms

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

    Measurements and exponents

    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
     للاسماء
    -0.67
     nahilalakip
    -0.57
    __*/
    -0.57
    ectoria
    -0.57
    enderror
    -0.56
    XmlAccessType
    -0.55
     ISNI
    -0.54
     سكانية
    -0.54
     defStyleAttr
    -0.54
    ddots
    -0.54
    POSITIVE LOGITS
    SizeMode
    0.52
    tagHelper
    0.49
    ✭✭
    0.48
    λων
    0.47
    queryInterface
    0.46
    quitous
    0.45
    щиеся
    0.45
    不起
    0.45
     Exacts
    0.43
    XR
    0.42
    Activations Density 6.464%

    No Known Activations