© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4334
    Prev
    Next
    INDEX
    Explanations

    negative sentiments expressed about bills, particularly energy bills

    oai_token-act-pair · gemini-2.0-flash

    energy bills

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     bill
    -2.70
     Bill
    -2.56
    bill
    -2.48
    Bill
    -2.44
     BILL
    -2.36
     bills
    -2.33
     Bills
    -2.28
    BILL
    -2.27
    bills
    -2.17
    Bills
    -2.09
    POSITIVE LOGITS
     Walkover
    0.56
    rawtypes
    0.55
     Oppen
    0.52
     okhttp
    0.50
     Camargo
    0.50
     Carrington
    0.49
     Wikispecies
    0.49
     Schuster
    0.47
     πυ
    0.47
    pentry
    0.46
    Activations Density 1.025%

    No Known Activations