© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12394
    Prev
    Next
    INDEX
    Explanations

    the expression "as a whole"

    oai_token-act-pair · gemini-2.0-flash

    generalize something as "whole"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     entire
    -3.17
    entire
    -2.84
     Entire
    -2.81
    Entire
    -2.48
     ENTIRE
    -2.45
    whole
    -2.30
    Whole
    -2.28
     whole
    -2.17
     Whole
    -1.99
     WHOLE
    -1.97
    POSITIVE LOGITS
    NavController
    0.56
    Geplaatst
    0.55
     సౌకర్య
    0.53
     Wayback
    0.52
    enterOuterAlt
    0.51
     fieldNum
    0.49
     lumen
    0.48
    Hmmmm
    0.47
     bụ
    0.47
    maphore
    0.47
    Activations Density 3.075%

    No Known Activations