© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12471
    Prev
    Next
    INDEX
    Explanations

    mentions of counters, signals, and counting, even when used in different languages

    oai_token-act-pair · gemini-2.0-flash

    counter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     mes
    -0.68
     Mes
    -0.66
    NING
    -0.64
    ning
    -0.63
     fla
    -0.62
    ding
    -0.60
    ltä
    -0.59
    mes
    -0.58
    Mes
    -0.57
     counter
    -0.56
    POSITIVE LOGITS
    Personendaten
    0.72
    ^(@)
    0.66
    SharedDtor
    0.64
    enderror
    0.61
    Unmarshaller
    0.60
     CreateTagHelper
    0.60
    execSQL
    0.60
     ویکی‌پدیای
    0.60
     hereof
    0.59
    ❋
    0.59
    Activations Density 5.645%

    No Known Activations