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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5009
    Prev
    Next
    INDEX
    Explanations

    indicators of possession like "my", "your", or their equivalents in other languages

    oai_token-act-pair · gemini-2.0-flash

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Sucesor
    -0.49
     jednym
    -0.43
    MenuGroup
    -0.42
     ImportError
    -0.42
     dessas
    -0.41
    thole
    -0.40
    ituation
    -0.40
     desses
    -0.40
    entist
    -0.40
    enei
    -0.39
    POSITIVE LOGITS
    StoreMessageInfo
    0.84
     للمعارف
    0.84
    routeProvider
    0.79
    sizeCache
    0.77
    []):
    0.75
    Története
    0.75
    новништво
    0.73
    WithIOException
    0.71
     our
    0.69
    ']):
    0.69
    Activations Density 2.252%

    No Known Activations