© 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. 754
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health risks, especially allergies and eye conditions as well as descriptions of geographic settlements

    oai_token-act-pair · gemini-2.0-flash

    year

    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
     linkovi
    -0.63
    Portale
    -0.61
     ErrIntOverflow
    -0.57
    RTEX
    -0.56
     المعيارى
    -0.56
    IContainer
    -0.56
    ReusableCell
    -0.54
     sekali
    -0.54
    GraphicsUnit
    -0.52
    Tikang
    -0.52
    POSITIVE LOGITS
     year
    3.11
    year
    2.47
     Year
    2.45
    Year
    2.42
     YEAR
    2.33
    YEAR
    2.09
     año
    1.91
     année
    1.83
     Jahr
    1.75
     yr
    1.52
    Activations Density 5.864%

    No Known Activations