© 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. 15076
    Prev
    Next
    INDEX
    Explanations

    tokens associated with facts and truth, and a proper name

    oai_token-act-pair · gemini-2.0-flash

    fact

    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
    getMenuInflater
    -0.57
     confronti
    -0.53
     "$(
    -0.48
    Framebuffer
    -0.47
    ENTITY
    -0.45
    amboo
    -0.44
     ""}
    -0.43
    JF
    -0.43
    jona
    -0.42
    EI
    -0.42
    POSITIVE LOGITS
    EDEFAULT
    0.77
    Personensuche
    0.77
     estekak
    0.75
    UnsafeEnabled
    0.65
    Hochspringen
    0.62
    dibles
    0.59
    apunov
    0.59
     InputDecoration
    0.59
    SpringBootTest
    0.57
    !*\
    0.57
    Activations Density 5.866%

    No Known Activations