© 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. 10789
    Prev
    Next
    INDEX
    Explanations

    pronouns, proper nouns, and verbs associated with developers and investments

    oai_token-act-pair · gemini-2.0-flash

    buy

    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
    MarshalTo
    -0.55
     Cipri
    -0.49
     Cocina
    -0.48
     Puoi
    -0.47
     cytoplasm
    -0.47
     bridle
    -0.46
    sträger
    -0.46
     yolk
    -0.46
    jspx
    -0.46
    gonic
    -0.46
    POSITIVE LOGITS
     buy
    2.19
     purchase
    2.17
     buying
    2.13
     bought
    2.09
     Purchase
    1.98
     buys
    1.98
    buy
    1.98
     purchased
    1.97
     Buy
    1.92
    buying
    1.87
    Activations Density 2.285%

    No Known Activations