© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10127
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, especially related to set theory, topology, and analysis

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    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
    boda
    -0.60
     AssemblyProduct
    -0.55
    äsident
    -0.52
    helial
    -0.51
    lüssel
    -0.50
     Widely
    -0.50
    spher
    -0.49
     [])
    -0.48
     [*]
    -0.47
    )=\
    -0.47
    POSITIVE LOGITS
    DebuggerNonUser
    0.58
     disponibilités
    0.55
    WireFormatLite
    0.55
    angliski
    0.52
    țul
    0.51
     خارجية
    0.48
    κη
    0.47
    ocry
    0.46
    ForValue
    0.46
     chi̍t
    0.45
    Activations Density 2.803%

    No Known Activations