© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10328
    Prev
    Next
    INDEX
    Explanations

    the word "window."

    oai_token-act-pair · gemini-2.0-flash

    window

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     végétale
    -0.60
    sidemargin
    -0.57
     blancas
    -0.56
     crónica
    -0.46
     sauvages
    -0.46
     caros
    -0.45
     logam
    -0.45
     Sixth
    -0.45
     bucal
    -0.45
    الثة
    -0.44
    POSITIVE LOGITS
     pinulongan
    0.70
    SequentialGroup
    0.67
    مصادر
    0.66
    مراجع
    0.65
    featureID
    0.63
    verwijspagina
    0.63
    vastava
    0.62
    Jeografia
    0.62
     defaultstate
    0.60
    🏻‍♀️
    0.59
    Activations Density 0.657%

    No Known Activations