© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14972
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and the verbs that follow them, indicating a person's habits, preferences and current activities.

    oai_token-act-pair · gemini-2.0-flash

    travel

    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
    AndEndTag
    -0.50
    ukone
    -0.50
    StructEnd
    -0.47
    GraphicsUnit
    -0.47
    GEBURTSDATUM
    -0.47
    artifactId
    -0.46
     pozy
    -0.46
    verwijspagina
    -0.46
    principalTable
    -0.45
    ArgumentParser
    -0.43
    POSITIVE LOGITS
     traveling
    0.83
     travelling
    0.82
     travel
    0.78
     Travelling
    0.78
     Traveling
    0.75
    Traveling
    0.71
    Travelling
    0.69
     traveled
    0.67
    traveling
    0.66
     viajar
    0.65
    Activations Density 2.404%

    No Known Activations