© 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. 14040
    Prev
    Next
    INDEX
    Explanations

    words related to technology instructions or documentation

    oai_token-act-pair · gemini-2.0-flash

    Books and manuals

    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
     correctes
    -0.70
    ArrowToggle
    -0.61
     spirituale
    -0.59
     الدولى
    -0.58
     picioare
    -0.57
     pouvoit
    -0.57
    GEBURTSDATUM
    -0.57
     Bearing
    -0.56
     >=",
    -0.56
     configureStore
    -0.56
    POSITIVE LOGITS
     book
    1.60
    book
    1.51
     Book
    1.34
    Book
    1.31
    BOOK
    1.26
     BOOK
    1.21
     libro
    1.02
     books
    0.96
     manual
    0.96
    books
    0.95
    Activations Density 2.229%

    No Known Activations