© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12297
    Prev
    Next
    INDEX
    Explanations

    strings of words that include "a" followed by a noun-phrase with "organization" or things related to taxes and non-profit status

    oai_token-act-pair · gemini-2.0-flash

    nonprofit organizations

    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
    writeFieldEnd
    -0.59
    Obrázky
    -0.57
    migrationBuilder
    -0.55
     استنادى
    -0.49
    Batis
    -0.47
    A
    -0.46
    mybatisplus
    -0.45
    λίου
    -0.45
    ynb
    -0.44
    Cour
    -0.44
    POSITIVE LOGITS
     linkovi
    0.67
     purpoſe
    0.58
     GeoNames
    0.58
     <<<<<<<<<<<<<<
    0.57
    ₅
    0.55
    ToProps
    0.54
     Cinco
    0.54
    OutputType
    0.52
     pleaſure
    0.52
     ۵
    0.52
    Activations Density 1.735%

    No Known Activations