© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11474
    Prev
    Next
    INDEX
    Explanations

    financial acronyms and regulatory terms.

    oai_token-act-pair · gemini-2.0-flash

    terms related to technical or regulatory language

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

    Financial/market analysis

    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
    ArrowToggle
    -0.73
    __":
    
    -0.73
     Archipelago
    -0.71
    ertale
    -0.71
    __':
    
    -0.71
     InputDecoration
    -0.71
     GenerationType
    -0.69
     Persians
    -0.65
     насељу
    -0.64
    Demografie
    -0.64
    POSITIVE LOGITS
    homonymie
    0.58
    //
    0.53
     relever
    0.45
    InvalidProtocol
    0.42
     short
    0.42
    put
    0.41
     put
    0.41
    positionen
    0.41
    rho
    0.40
    TagHelper
    0.40
    Activations Density 1.008%

    No Known Activations