© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    first and second person references, and expressions of urgency

    oai_token-act-pair · gemini-2.0-flash

    comma or "I"

    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
     متعلقه
    -0.87
    SharedDtor
    -0.65
     NUKAT
    -0.59
    jaros
    -0.57
     ProtoMessage
    -0.55
    ')";
    -0.53
    Биография
    -0.52
     depic
    -0.52
     betweenstory
    -0.52
    LookAnd
    -0.52
    POSITIVE LOGITS
     defaultstate
    0.76
    WithMany
    0.68
    TargetException
    0.54
    strategic
    0.54
     thereof
    0.51
    newState
    0.51
    ⓧ
    0.51
    -------
    0.51
    BURGH
    0.51
    녕
    0.49
    Activations Density 1.551%

    No Known Activations