© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8322
    Prev
    Next
    INDEX
    Explanations

    references to physical locations, like states, countries, districts or towns, and also materials.

    oai_token-act-pair · gemini-2.0-flash

    state or material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     open
    -0.66
     Open
    -0.58
    Open
    -0.54
    open
    -0.52
     mem
    -0.52
    stle
    -0.52
    haf
    -0.50
    setFlags
    -0.49
    期
    -0.48
     Salazar
    -0.48
    POSITIVE LOGITS
    expandindo
    1.20
    RenderAtEndOf
    1.12
     '\\;'
    1.12
    LookAnd
    1.11
    complexContent
    1.02
     فريبيس
    1.01
    ]")]
    0.96
    GEBURTSDATUM
    0.95
     ujednoznacz
    0.91
     виправивши
    0.90
    Activations Density 0.524%

    No Known Activations