© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3527
    Prev
    Next
    INDEX
    Explanations

    words associated with Irish cycling races and their winners

    oai_token-act-pair · gemini-2.0-flash

    Irish

    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
    IndentedString
    -0.55
    omia
    -0.50
     propOrder
    -0.49
    eningen
    -0.48
    ents
    -0.47
     کره
    -0.47
     IMDG
    -0.47
     Nao
    -0.47
    merz
    -0.47
    getTag
    -0.46
    POSITIVE LOGITS
     Normdatei
    0.62
    RenderAtEndOf
    0.58
    bitat
    0.56
     féd
    0.53
     مرئيه
    0.52
    InputBorder
    0.52
     dAtA
    0.51
     !}
    0.49
     National
    0.49
     POINT
    0.48
    Activations Density 1.586%

    No Known Activations