Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12147
    Prev
    Next
    INDEX
    Explanations

    words relating to process management, data handling, and systems operation.

    oai_token-act-pair · gemini-2.0-flash

    adverbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AsUp
    -0.63
    LEncoder
    -0.60
    oredCriteria
    -0.60
     صوتيه
    -0.58
    ngrx
    -0.56
     transférez
    -0.56
     juger
    -0.56
    InstrumentedTest
    -0.56
     déput
    -0.55
     générer
    -0.55
    POSITIVE LOGITS
     quickly
    0.62
     safely
    0.51
     closely
    0.51
     forfeit
    0.50
     arşivlendi
    0.49
     conveniently
    0.48
    quad
    0.48
     swiftly
    0.47
     smoothly
    0.47
     quai
    0.47
    Activations Density 6.781%

    No Known Activations