© 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. 10062
    Prev
    Next
    INDEX
    Explanations

    tokens near prepositions like "from", "of", and "to", as well as abbreviations related to football/soccer

    oai_token-act-pair · gemini-2.0-flash

    Categories and locations

    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
    糸
    -0.40
    ExecutorService
    -0.39
     heli
    -0.39
    InSection
    -0.38
     ili
    -0.37
     Hanging
    -0.36
    onya
    -0.36
    وست
    -0.35
    uto
    -0.35
     liberty
    -0.34
    POSITIVE LOGITS
    AndEndTag
    0.85
     ProtoMessage
    0.77
    sizeCache
    0.77
     nahilalakip
    0.75
    цездатний
    0.75
    kloped
    0.74
    IntoConstraints
    0.74
    +#+
    0.74
    TagMode
    0.73
    ++]
    0.72
    Activations Density 0.346%

    No Known Activations