© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6398
    Prev
    Next
    INDEX
    Explanations

    sports reporting, particularly basketball, including team names, player names, and game-related terms

    oai_token-act-pair · gemini-2.0-flash

    Program names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     NSCoder
    -0.68
     utafitiHapana
    -0.63
     Waray
    -0.61
    afficheront
    -0.57
     Typ
    -0.57
     Techn
    -0.56
     Cuad
    -0.54
     Cables
    -0.54
     Wib
    -0.54
    nhs
    -0.53
    POSITIVE LOGITS
    visiae
    0.51
    IndentedString
    0.48
    formazioni
    0.46
    ROLS
    0.45
     CreateTagHelper
    0.45
    tefan
    0.45
    WireFormatLite
    0.45
    PreExecute
    0.44
    ManagedBean
    0.43
    orian
    0.43
    Activations Density 0.632%

    No Known Activations