© 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. 6270
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and sections of text related to real estate, construction projects, or legal documentation.

    oai_token-act-pair · gemini-2.0-flash

    references to councils or council-related topics

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

    Local government

    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
     disambiguazione
    -0.87
    SpringBootTest
    -0.85
    
    -0.84
    WebServlet
    -0.82
    Portail
    -0.70
    Билгалдахарш
    -0.66
    المشاركات
    -0.64
     Protobuf
    -0.64
     Efq
    -0.61
    Gambas
    -0.60
    POSITIVE LOGITS
     Council
    0.60
     council
    0.58
    council
    0.53
     VIEW
    0.51
    XmlAccessType
    0.49
     viewing
    0.49
     popular
    0.49
    lot
    0.49
     COUNCIL
    0.48
     View
    0.48
    Activations Density 0.373%

    No Known Activations