© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4425
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, and initialisms

    oai_token-act-pair · gemini-2.0-flash

    Specific proper nouns/jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     her
    -0.57
     ve
    -0.48
    ❷
    -0.48
    Magdalena
    -0.47
     ven
    -0.47
     s
    -0.47
     normal
    -0.46
    печат
    -0.46
    azzi
    -0.45
    ']?>
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    1.05
     themſelves
    0.95
    IntoConstraints
    0.87
     المعيارى
    0.80
     myſelf
    0.79
    seamnă
    0.77
     GenerationType
    0.77
    Personensuche
    0.75
    RegistryLite
    0.75
     photolibrary
    0.75
    Activations Density 11.175%

    No Known Activations