© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12809
    Prev
    Next
    INDEX
    Explanations

    words in technical or scientific texts that specify a condition or comparison.

    oai_token-act-pair · gemini-2.0-flash

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     estekak
    -0.94
    abestanden
    -0.93
     itſelf
    -0.88
    ImageContext
    -0.87
     Tiberius
    -0.86
    Sklici
    -0.85
    XmlEnum
    -0.85
    ंदीखरीदारी
    -0.85
     disambiguazione
    -0.84
     Taktlose
    -0.83
    POSITIVE LOGITS
    tagna
    0.47
     standard
    0.44
     y
    0.42
     Sal
    0.42
     can
    0.41
     sz
    0.41
     so
    0.40
     (
    0.40
     sal
    0.40
    ↵
    0.39
    Activations Density 1.372%

    No Known Activations