© 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. 5632
    Prev
    Next
    INDEX
    Explanations

    code syntax related to user interface manipulation

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming or code syntax

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

    code/programming

    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
    ()):
    -0.50
     fixed
    -0.46
     Jewish
    -0.45
     inv
    -0.45
    ());
    -0.45
    fetchall
    -0.44
    fixed
    -0.43
     forti
    -0.42
    sol
    -0.42
     Sol
    -0.42
    POSITIVE LOGITS
     lenker
    0.77
    Tikang
    0.63
     يتيمه
    0.63
    
    0.63
     wikipagina
    0.61
    يميديا
    0.61
     EconPapers
    0.60
     himo
    0.60
     >=",
    0.60
    Kaynakça
    0.59
    Activations Density 1.968%

    No Known Activations