© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3358
    Prev
    Next
    INDEX
    Explanations

    words, abbreviations, and names related to viruses, locations, law, and feelings.

    oai_token-act-pair · gemini-2.0-flash

    ter

    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
     ter
    -1.16
    Ter
    -1.06
     Ter
    -1.02
    ter
    -1.01
    TER
    -0.89
    ters
    -0.87
     TER
    -0.81
    iter
    -0.63
    тер
    -0.62
    TERS
    -0.57
    POSITIVE LOGITS
    +#+#
    0.80
     defaultstate
    0.75
     AssemblyCulture
    0.74
     useState
    0.71
    AndEndTag
    0.69
    TagMode
    0.69
     للمعارف
    0.68
    NameInMap
    0.65
    toHave
    0.63
    География
    0.61
    Activations Density 15.012%

    No Known Activations