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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14048
    Prev
    Next
    INDEX
    Explanations

    mentions of reading devices and books

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'stay'

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

    stay

    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
    Chham
    -0.40
    gewä
    -0.38
    קישורים
    -0.38
     T
    -0.37
    خی
    -0.33
    المصادر
    -0.33
    рга
    -0.33
    sem
    -0.33
    oflavin
    -0.33
    isement
    -0.32
    POSITIVE LOGITS
     stays
    1.04
     Stays
    1.02
     stay
    0.99
     staying
    0.99
     stayed
    0.98
     resourceCulture
    0.95
     Stay
    0.95
    stay
    0.94
    stays
    0.93
     Staying
    0.92
    Activations Density 3.434%

    No Known Activations