© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11546
    Prev
    Next
    INDEX
    Explanations

    relationships between two entities expressed as "one ... and the other," or in the context of other prepositions and grammar

    oai_token-act-pair · gemini-2.0-flash

    Relationships between two things

    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
    spesies
    -0.65
     Maro
    -0.50
    pośred
    -0.48
     CreateTagHelper
    -0.47
    ĩa
    -0.46
    BibitemShut
    -0.46
    bibinfo
    -0.44
    __]
    -0.44
    wixt
    -0.44
    &__
    -0.43
    POSITIVE LOGITS
     nakalista
    0.60
     StatefulWidget
    0.56
    ApplicationTests
    0.54
     surla
    0.52
    tagHelperRunner
    0.52
    esgue
    0.52
    Xna
    0.51
    providedIn
    0.50
    kháu
    0.50
    CodeDom
    0.49
    Activations Density 10.848%

    No Known Activations