© 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. 6726
    Prev
    Next
    INDEX
    Explanations

    mentions of people named Martin

    oai_token-act-pair · gemini-2.0-flash

    instances of the name "Martin"

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

    Martin

    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
     kaarangay
    -0.72
     Theſe
    -0.68
     photolibrary
    -0.67
     draught
    -0.66
    CodedInputStream
    -0.65
     fubject
    -0.64
     Shrub
    -0.64
     Boron
    -0.63
     precedence
    -0.62
     horseshoe
    -0.62
    POSITIVE LOGITS
    trup
    0.50
    uxxxx
    0.49
    haja
    0.49
    hausen
    0.48
     cuello
    0.48
     F
    0.48
    Viited
    0.47
     G
    0.46
    vertra
    0.46
    ya
    0.45
    Activations Density 0.473%

    No Known Activations