© 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. 4872
    Prev
    Next
    INDEX
    Explanations

    financial information pertaining to company growth, especially revenue growth from pharmaceutical sales in and outside the United States, over multiple years

    oai_token-act-pair · gemini-2.0-flash

    financial reports and growth

    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
    writeFieldEnd
    -0.66
    ########.
    -0.66
    verwijspagina
    -0.65
    uxxxx
    -0.64
     mergeFrom
    -0.63
    GIVEREF
    -0.59
    makeConstraints
    -0.59
    Uninitialized
    -0.58
    parsedMessage
    -0.57
     محفوظة
    -0.56
    POSITIVE LOGITS
    سرائيلي
    0.48
    ."</
    0.45
    riceps
    0.44
     VIDEOTAPE
    0.43
     án
    0.43
    DialogContent
    0.42
    DatabaseError
    0.42
    StoreMessageInfo
    0.42
    panic
    0.41
    geset
    0.41
    Activations Density 3.457%

    No Known Activations