© 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. 6334
    Prev
    Next
    INDEX
    Explanations

    code from programming languages

    oai_token-act-pair · gemini-2.0-flash

    say "w" words

    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
     We
    -0.84
     You
    -0.71
     W
    -0.54
    You
    -0.52
     Nous
    -0.52
     Мы
    -0.51
     Vous
    -0.51
     Was
    -0.51
    We
    -0.50
     Well
    -0.49
    POSITIVE LOGITS
     w
    0.93
     wo
    0.73
    webElementXpaths
    0.69
     wä
    0.65
    wo
    0.65
     wa
    0.64
     wh
    0.63
     wah
    0.63
     wireType
    0.61
    wid
    0.60
    Activations Density 8.031%

    No Known Activations