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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14705
    Prev
    Next
    INDEX
    Explanations

    language describing finance and sales, associating a product or service with affordable value.

    oai_token-act-pair · gemini-2.0-flash

    prices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     price
    -0.68
    price
    -0.66
     harganya
    -0.62
    Price
    -0.58
     ErrIntOverflow
    -0.53
     Price
    -0.52
    KURZBESCHREIBUNG
    -0.52
     PRICE
    -0.52
     coû
    -0.51
    Prices
    -0.50
    POSITIVE LOGITS
     competitive
    1.45
     fair
    1.23
    competitive
    1.22
     Competitive
    1.20
     reasonable
    1.20
    Competitive
    1.14
     competi
    1.03
     low
    0.98
     competitiveness
    0.97
     competitively
    0.97
    Activations Density 2.032%

    No Known Activations