© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6425
    Prev
    Next
    INDEX
    Explanations

    text about a steering wheel in a Peugeot car

    oai_token-act-pair · gemini-2.0-flash

    vehicles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    
    -0.96
    AndEndTag
    -0.79
    contentLoaded
    -0.75
    StructEnd
    -0.72
     QtCore
    -0.70
    UserScript
    -0.69
    yarnpkg
    -0.68
    Abitanti
    -0.67
    abetes
    -0.66
    الحياه
    -0.65
    POSITIVE LOGITS
     cast
    0.57
     cơ
    0.51
     adjustable
    0.50
     Adjustable
    0.50
     prost
    0.48
     rotation
    0.45
    bida
    0.45
    cast
    0.44
    anci
    0.44
     metal
    0.43
    Activations Density 1.237%

    No Known Activations