© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    articles (the, a, an) and the word 'the' or capitalized 'The' at the beginning of a sentence or quote

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     eccell
    -0.52
    }}}}
    -0.51
     accanto
    -0.50
     riusc
    -0.47
    These
    -0.46
    Why
    -0.45
     kiin
    -0.45
     vejo
    -0.45
     acompañado
    -0.44
     énergé
    -0.43
    POSITIVE LOGITS
    saraba
    0.72
     primary
    0.66
     Primary
    0.61
    itisation
    0.56
    transQ
    0.54
     propOrder
    0.54
    הערות
    0.54
    Lähteet
    0.53
    aarrggbb
    0.53
    новниш
    0.52
    Activations Density 6.656%

    No Known Activations