© 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. 15691
    Prev
    Next
    INDEX
    Explanations

    instances of organizations, committees, and other groups of people working together.

    oai_token-act-pair · gemini-2.0-flash

    organizations/places

    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
    pyplot
    -0.49
    ⓘ
    -0.46
    /*
    -0.45
    袍
    -0.43
     remot
    -0.41
    and
    -0.41
     Sarg
    -0.40
     phạm
    -0.40
    TextWatcher
    -0.40
     defaultstate
    -0.40
    POSITIVE LOGITS
     exemplaires
    0.64
     UNC
    0.58
    FieldBuilder
    0.57
    didSet
    0.57
    цездатний
    0.56
    pædia
    0.56
    rizona
    0.56
    IUrlHelper
    0.56
    hassee
    0.55
    yttä
    0.54
    Activations Density 12.841%

    No Known Activations