© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9027
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, and sometimes pronouns like "it" and "there". Technically that means it's not *just* proper nouns - it's finding noun phrases

    oai_token-act-pair · gemini-2.0-flash

    End

    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
     protoimpl
    -0.87
     EconPapers
    -0.80
     HasFactory
    -0.78
    
    -0.76
    OrNil
    -0.76
     typelib
    -0.75
    RenderAtEndOf
    -0.73
    OGND
    -0.73
    AccessorTable
    -0.71
    Filmografie
    -0.71
    POSITIVE LOGITS
    <bos>
    1.13
     we
    0.68
     they
    0.54
    TryGetValue
    0.52
    зулта
    0.52
    ępnie
    0.51
    '
    0.49
    ’
    0.45
     
    0.44
    we
    0.44
    Activations Density 1.765%

    No Known Activations