© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14537
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations and their leadership

    oai_token-act-pair · gemini-2.0-flash

    Hall or Vice

    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
     Hall
    -1.05
     hall
    -1.02
    Hall
    -0.98
     HALL
    -0.94
    hall
    -0.92
     vice
    -0.89
     halls
    -0.85
    HALL
    -0.83
     Halls
    -0.77
     Vice
    -0.73
    POSITIVE LOGITS
    GEBURTS
    0.59
     Roskov
    0.59
    ATRO
    0.57
    geth
    0.54
     hins
    0.54
    jupiter
    0.52
    الغ
    0.52
    ⁴
    0.52
    idosis
    0.52
    gnancy
    0.52
    Activations Density 7.840%

    No Known Activations