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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10012
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and numerical references

    oai_token-act-pair · 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
    not
    -0.50
    well
    -0.47
    set
    -0.45
    way
    -0.45
    ko
    -0.44
    par
    -0.44
    hygiène
    -0.43
    pro
    -0.42
    ükemmel
    -0.42
    part
    -0.42
    POSITIVE LOGITS
    elry
    0.56
    ologists
    0.55
    itions
    0.54
    AutoScaleMode
    0.54
    Semitism
    0.54
    ees
    0.54
    AOS
    0.53
    eration
    0.52
    equ
    0.52
    elected
    0.52
    Activations Density 15.098%

    No Known Activations