© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13463
    Prev
    Next
    INDEX
    Explanations

    strings of tokens common in scientific publications, especially tokens relating to locations, studies, and chemicals

    oai_token-act-pair · gemini-2.0-flash

    IHC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     آر
    -0.50
     rendus
    -0.47
    sink
    -0.46
    ISSION
    -0.45
     kalau
    -0.43
    jut
    -0.42
     rend
    -0.42
    inį
    -0.42
    сюда
    -0.42
    IANO
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    1.03
    expandindo
    0.96
    AccessorTable
    0.86
     wireType
    0.83
    IntoConstraints
    0.79
     للاسماء
    0.78
     препратки
    0.77
    transQ
    0.77
    DebuggerNonUser
    0.74
    сылкі
    0.74
    Activations Density 3.220%

    No Known Activations