© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 809
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate something changing

    oai_token-act-pair · gemini-2.0-flash

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.67
    PreferredItem
    -0.65
     resourceCulture
    -0.60
    archiviato
    -0.60
    ❋
    -0.60
    MemoryWarning
    -0.58
    openzeppelin
    -0.57
     TestBed
    -0.57
     way
    -0.56
     Way
    -0.56
    POSITIVE LOGITS
     Efq
    0.58
     to
    0.55
     المعيارى
    0.54
     plagioclase
    0.52
     الحره
    0.51
     frequency
    0.50
     Herrick
    0.49
     Alfaro
    0.47
     queens
    0.47
     poisons
    0.47
    Activations Density 9.302%

    No Known Activations