© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11228
    Prev
    Next
    INDEX
    Explanations

    language related to sports statistics or performance measurements

    oai_token-act-pair · gemini-2.0-flash

    basketball

    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
    protoimpl
    -0.68
     field
    -0.67
     Unmarshal
    -0.67
     Mero
    -0.64
    tvguidetime
    -0.62
     FIELD
    -0.62
     nahilalakip
    -0.59
    Vidite
    -0.59
     Field
    -0.57
    mability
    -0.57
    POSITIVE LOGITS
    ToInt
    0.48
     án
    0.47
     Eccl
    0.44
    슬
    0.43
    Predecesor
    0.42
     mínimos
    0.41
     tuong
    0.41
     renang
    0.39
     nervios
    0.39
    SwingConstants
    0.39
    Activations Density 0.253%

    No Known Activations