© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9184
    Prev
    Next
    INDEX
    Explanations

    words related to handling and supporting tasks in programming or transportation

    oai_token-act-pair · gemini-2.0-flash

    handle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Localisation
    -0.53
    bux
    -0.50
     authService
    -0.49
    [][]
    -0.42
     ropa
    -0.42
    AsyncResult
    -0.42
    downloads
    -0.40
     researcher
    -0.40
     lokal
    -0.40
    vic
    -0.40
    POSITIVE LOGITS
     handling
    1.30
     handles
    1.29
     handled
    1.29
     Handle
    1.25
     handle
    1.25
     Handles
    1.17
    <bos>
    1.12
     Handling
    1.11
    handled
    1.09
    handling
    1.06
    Activations Density 1.054%

    No Known Activations