© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10368
    Prev
    Next
    INDEX
    Explanations

    questions that directly address someone else, especially using "you"

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    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
     cuello
    -0.48
    rq
    -0.43
    setCharacter
    -0.43
     agricoles
    -0.43
    PIS
    -0.43
     traff
    -0.43
     directores
    -0.43
    CHAR
    -0.43
    PPM
    -0.43
    kolen
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
     onCreateView
    0.80
     CURIAM
    0.75
    SBATCH
    0.72
    AddTagHelper
    0.72
    ExecuteReader
    0.69
    InjectAttribute
    0.69
     propOrder
    0.67
    #
    0.66
     noDo
    0.66
    Activations Density 0.886%

    No Known Activations