© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11438
    Prev
    Next
    INDEX
    Explanations

    mentions of basketball game statistics

    oai_token-act-pair · gemini-2.0-flash

    sports scores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    OGND
    -1.01
    AddTagHelper
    -0.66
    awaiter
    -0.65
     estimés
    -0.64
     Wikimedijinoj
    -0.64
     scale
    -0.62
     protoimpl
    -0.60
    AccessorTable
    -0.60
    reportWebVitals
    -0.59
     Scale
    -0.59
    POSITIVE LOGITS
     field
    0.58
     FIELD
    0.52
     Waray
    0.51
     ProtoMessage
    0.51
     disponibilités
    0.50
    élien
    0.48
    field
    0.48
    Field
    0.47
    FIELD
    0.46
    pielt
    0.44
    Activations Density 0.736%

    No Known Activations