© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13301
    Prev
    Next
    INDEX
    Explanations

    the word "though"

    oai_token-act-pair · gemini-2.0-flash

    though

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     though
    -2.88
    though
    -2.39
     THOUGH
    -2.28
     Though
    -1.98
    Though
    -1.98
     tho
    -1.44
     entanto
    -1.32
     although
    -1.19
     हालांकि
    -1.17
     however
    -1.16
    POSITIVE LOGITS
     CGRectMake
    0.59
    出版年
    0.58
    payers
    0.56
     actionPerformed
    0.56
     onCreateView
    0.55
    esModule
    0.54
    іга
    0.52
    WithMany
    0.52
    ibatis
    0.50
     sqlSession
    0.49
    Activations Density 0.141%

    No Known Activations