© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15778
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dollar amounts and prices.

    oai_token-act-pair · gemini-2.0-flash

    numbers ending in 0 or 5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    styleType
    -0.72
    __((
    -0.64
     Réponses
    -0.62
     يتيمه
    -0.60
    
    -0.58
    TProtocol
    -0.57
    asties
    -0.56
    MigrationBuilder
    -0.56
     gawas
    -0.55
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.55
    zeera
    0.47
     dollar
    0.46
     including
    0.45
    Fixes
    0.42
    /$
    0.41
     fără
    0.41
    ConstraintMaker
    0.40
    icin
    0.40
    JHEP
    0.40
    Activations Density 1.750%

    No Known Activations