© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    words suggesting responsibilities, governance, or being based on something

    oai_token-act-pair · gemini-2.0-flash

    say prepositions

    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
     betweenstory
    -1.23
     TextAppearance
    -1.06
     Мексичка
    -1.04
     дописавши
    -1.02
     ویکی‌پدی
    -0.99
     Италијани
    -0.98
    Pozri
    -0.98
    NewUrlParser
    -0.96
    expandindo
    -0.95
    RegistryLite
    -0.93
    POSITIVE LOGITS
     alternately
    0.44
     conscienti
    0.34
     wisely
    0.34
     preferentially
    0.34
     ruth
    0.34
     SNR
    0.33
     CMV
    0.32
     intimately
    0.32
     rightly
    0.32
     SCS
    0.32
    Activations Density 25.304%

    No Known Activations