© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6119
    Prev
    Next
    INDEX
    Explanations

    the word "terms"

    oai_token-act-pair · gemini-2.0-flash

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     terms
    -2.31
    terms
    -1.80
     Terms
    -1.66
     termes
    -1.66
     TERMS
    -1.64
    Terms
    -1.61
     termos
    -1.53
     términos
    -1.49
    TERMS
    -1.36
     term
    -1.14
    POSITIVE LOGITS
    TagMode
    0.65
    Lähteet
    0.62
    ientôt
    0.60
    QMetaType
    0.60
    tagHelperRunner
    0.60
     combineReducers
    0.59
     RouterModule
    0.57
     FileInputStream
    0.56
    InputBorder
    0.56
     مشين
    0.54
    Activations Density 1.381%

    No Known Activations