© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1942
    Prev
    Next
    INDEX
    Explanations

    words related to organization, management, and tribute

    oai_token-act-pair · gemini-2.0-flash

    organizing and arranging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     organized
    -2.80
     organised
    -2.78
     organize
    -2.75
     Organized
    -2.73
     organise
    -2.66
     organizing
    -2.63
     organising
    -2.53
     Organize
    -2.53
    Organized
    -2.52
    organized
    -2.48
    POSITIVE LOGITS
     forKey
    0.44
    netje
    0.44
    freiheit
    0.42
    łbym
    0.42
    HasForeignKey
    0.42
     bedrijven
    0.41
     tersangka
    0.41
    JspWriter
    0.41
    ően
    0.41
    県道
    0.40
    Activations Density 1.860%

    No Known Activations