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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14309
    Prev
    Next
    INDEX
    Explanations

    occurrences of percentages and related words in numerical data

    oai_token-act-pair · gemini-2.0-flash

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    %
    -1.59
     \%$
    -1.43
    \%
    -1.30
     %
    -1.22
     percent
    -1.19
    %)
    -1.18
     (%)
    -1.18
    percent
    -1.13
    %'
    -1.13
     \%}$
    -1.11
    POSITIVE LOGITS
    Crédit
    0.48
    PDIR
    0.48
    Traduction
    0.46
    uests
    0.46
    bringer
    0.46
    foy
    0.45
     cref
    0.45
    raught
    0.44
     vux
    0.44
     crock
    0.43
    Activations Density 4.087%

    No Known Activations