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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3904
    Prev
    Next
    INDEX
    Explanations

    code snippets related to the game Tic-Tac-Toe and turn management

    oai_token-act-pair · gemini-2.0-flash

    computer code or foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    abit
    -0.56
     विश्वसनीयता
    -0.53
     ziren
    -0.53
    XmlAccessorType
    -0.52
    bjs
    -0.51
     le
    -0.51
     dones
    -0.50
     <=",
    -0.50
     Betten
    -0.49
    /**
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.68
     EconPapers
    0.62
     est
    0.56
    ValueStyle
    0.56
    :✨
    0.55
    Geplaatst
    0.55
     nahilalakip
    0.55
    INSEE
    0.54
    KommentareTeilen
    0.52
     onCreateView
    0.52
    Activations Density 0.809%

    No Known Activations