© 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. 14585
    Prev
    Next
    INDEX
    Explanations

    terms related to finance, especially stock market valuation

    oai_token-act-pair · gemini-2.0-flash

    zero

    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
     makeStyles
    -0.77
    ंदीखरीदारी
    -0.74
     šķ
    -0.68
    AutoScaleMode
    -0.66
    MLLoader
    -0.64
     excès
    -0.61
    expandindo
    -0.61
     nakalista
    -0.60
    viale
    -0.59
     例证
    -0.59
    POSITIVE LOGITS
    ,
    0.65
    .
    0.64
     which
    0.63
    !
    0.59
    ;
    0.59
    ).
    0.55
     based
    0.55
     (
    0.54
     since
    0.54
     in
    0.54
    Activations Density 16.004%

    No Known Activations