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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12123
    Prev
    Next
    INDEX
    Explanations

    words relating to travel, journeys and events

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    protoc
    -0.50
     events
    -0.50
    events
    -0.49
    IANGLES
    -0.48
     mengajar
    -0.48
     trips
    -0.46
    event
    -0.46
     event
    -0.46
    Events
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.81
     EdgeInsets
    0.68
    +:+
    0.63
    OrBuilder
    0.57
     ***!
    0.56
     BorderSide
    0.56
    llary
    0.54
    HasAnnotation
    0.54
    complexContent
    0.53
    <!--[
    0.53
    Activations Density 6.064%

    No Known Activations