© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12321
    Prev
    Next
    INDEX
    Explanations

    the number "100" or words associated with land area

    oai_token-act-pair · gemini-2.0-flash

    quantities related to thousands

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

    Thousands

    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
     acres
    -0.62
    apimachinery
    -0.61
     estimés
    -0.60
     nonatomic
    -0.57
     acre
    -0.56
    abases
    -0.56
    脚注の使い方
    -0.56
    GOTREF
    -0.55
    ]--;
    -0.53
    setViewportView
    -0.53
    POSITIVE LOGITS
     thousands
    0.63
    thousands
    0.56
     thousand
    0.54
     pauvreté
    0.54
     Thousand
    0.53
    ########.
    0.53
    Thousand
    0.52
     polaire
    0.50
     Manas
    0.50
     Thousands
    0.49
    Activations Density 1.732%

    No Known Activations