© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9687
    Prev
    Next
    INDEX
    Explanations

    numbers used in science, statistics, and history

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical/logical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -2.00
     Jefus
    -0.56
    __":
    -0.49
    hdys
    -0.48
     typelib
    -0.48
     kuin
    -0.47
    CFLAGS
    -0.47
     kasarigan
    -0.47
    __':
    -0.45
     Theſe
    -0.44
    POSITIVE LOGITS
    igshid
    0.72
    ⓧ
    0.66
    DOCTYPE
    0.62
    PerformLayout
    0.62
    readystatechange
    0.61
    eqn
    0.60
    GrantedAuthority
    0.57
    UPI
    0.56
    ocellular
    0.54
     ý
    0.52
    Activations Density 24.348%

    No Known Activations