© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8587
    Prev
    Next
    INDEX
    Explanations

    text about Formula 1 racing games

    oai_token-act-pair · gemini-2.0-flash

    Video games

    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
    NameInMap
    -0.76
    enumi
    -0.76
     resourceCulture
    -0.73
    AnchorStyles
    -0.69
    tonsoft
    -0.67
    Tembelea
    -0.66
    ValueGeneration
    -0.66
    DockStyle
    -0.64
    henswürdigkeiten
    -0.63
     صوتيه
    -0.63
    POSITIVE LOGITS
     bambou
    0.45
    masalah
    0.44
     urbain
    0.44
    鏽
    0.43
    SharedCtor
    0.41
     zod
    0.41
     taas
    0.40
     comprends
    0.39
    ([
    0.39
     rispetto
    0.39
    Activations Density 1.203%

    No Known Activations