© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6286
    Prev
    Next
    INDEX
    Explanations

    place names, political entities, economic terms, and education-related terms

    oai_token-act-pair · gemini-2.0-flash

    entities related to organizations or establishments

    np_token-act-pair-logits · gpt-4o-mini

    location descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ParallelGroup
    -0.71
    lgari
    -0.63
    RegistryLite
    -0.56
     itſelf
    -0.52
    󠁴
    -0.52
     suivante
    -0.50
    featureID
    -0.50
    存于互联网档案馆
    -0.49
    Viki
    -0.48
    IsMutable
    -0.45
    POSITIVE LOGITS
     company
    0.85
    DockStyle
    0.73
     hotel
    0.69
     organization
    0.69
    company
    0.69
     city
    0.68
     church
    0.68
     restaurant
    0.64
     town
    0.63
     colony
    0.63
    Activations Density 5.366%

    No Known Activations