© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16290
    Prev
    Next
    INDEX
    Explanations

    code, especially characters indicating the end of statements or blocks

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     فريبيس
    -0.69
     ujednoznacz
    -0.57
    rungsseite
    -0.57
     للمعارف
    -0.57
     Walkover
    -0.56
    toggler
    -0.56
    PreferredItem
    -0.55
     déf
    -0.54
     Vesta
    -0.54
    QMetaType
    -0.53
    POSITIVE LOGITS
     propOrder
    0.50
    Hochspringen
    0.48
    Pyx
    0.47
    roppo
    0.45
     generation
    0.44
    TagMode
    0.42
    onomía
    0.42
    CCER
    0.41
    énario
    0.41
     Inters
    0.41
    Activations Density 0.679%

    No Known Activations