© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12159
    Prev
    Next
    INDEX
    Explanations

    words related to government and internal affairs

    oai_token-act-pair · gemini-2.0-flash

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     internal
    -2.27
    internal
    -2.06
     Internal
    -2.02
    Internal
    -2.02
     external
    -1.88
    external
    -1.77
     External
    -1.74
     INTERNAL
    -1.70
    External
    -1.70
    INTERNAL
    -1.65
    POSITIVE LOGITS
    EndGlobalSection
    0.99
     насељу
    0.93
     Chwiliwch
    0.88
    WithIOException
    0.85
    UnknownFieldSet
    0.85
    principalTable
    0.79
     ArrayAdapter
    0.77
     &___
    0.73
     moschino
    0.73
     يتيمه
    0.72
    Activations Density 13.409%

    No Known Activations