© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3936
    Prev
    Next
    INDEX
    Explanations

    capitalized letters and two-letter combinations "pt", "hs", "Q", "v", "C" and "b"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    i
    -0.85
    c
    -0.81
    a
    -0.80
    e
    -0.80
    '
    -0.80
    w
    -0.77
    o
    -0.77
    m
    -0.76
    (
    -0.76
    f
    -0.75
    POSITIVE LOGITS
     itſelf
    1.21
    ſelf
    1.13
    BibitemShut
    1.12
    ſelves
    1.11
    leſs
    1.11
     $_"
    1.09
    VIRONMENT
    1.09
    neſs
    1.07
    ^(@)
    1.06
    .}~\
    1.05
    Activations Density 2.652%

    No Known Activations