© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 549
    Prev
    Next
    INDEX
    Explanations

    code from a variety of programming languages, including C, LaTeX, and Lua

    oai_token-act-pair · gemini-2.0-flash

    computer code/math

    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
    gered
    -0.49
    yf
    -0.47
    cektir
    -0.44
    ging
    -0.43
    yay
    -0.43
    yc
    -0.42
    aysia
    -0.41
    y
    -0.40
    vins
    -0.40
    wort
    -0.40
    POSITIVE LOGITS
    men
    0.75
    Jîn
    0.63
    ms
    0.63
    man
    0.62
    me
    0.60
    mo
    0.60
     незавершена
    0.59
    m
    0.59
     EconPapers
    0.58
     propOrder
    0.58
    Activations Density 12.751%

    No Known Activations