© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10736
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     الحره
    -0.50
     houſe
    -0.47
     Propriété
    -0.46
     Surfer
    -0.45
     paro
    -0.45
     permiti
    -0.45
     Vierge
    -0.44
    henge
    -0.44
     Houſe
    -0.44
     marlin
    -0.44
    POSITIVE LOGITS
     nakalista
    0.70
     <<<<<<<<<<<<<<
    0.68
    
    0.68
    رشف
    0.64
    onViewCreated
    0.63
    ArrowToggle
    0.63
    IBOutlet
    0.62
    Personensuche
    0.61
     estekak
    0.58
    Tembelea
    0.58
    Activations Density 0.623%

    No Known Activations