© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    words about providing a service

    oai_token-act-pair · gemini-2.0-flash

    service

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    si
    -0.47
    st
    -0.47
    stro
    -0.47
     témoin
    -0.47
    νώ
    -0.46
    stoke
    -0.45
    stine
    -0.45
    isms
    -0.45
    KommentareTeilen
    -0.43
     Peep
    -0.43
    POSITIVE LOGITS
     متعلقه
    0.84
    ніципалі
    0.68
     <>",
    0.66
     ujednoznacz
    0.60
    曖昧さ回避
    0.57
     disambiguazione
    0.57
    äsident
    0.56
    :[]
    0.55
    grà
    0.55
     المعيارى
    0.53
    Activations Density 6.814%

    No Known Activations