© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7727
    Prev
    Next
    INDEX
    Explanations

    text from configuration files containing UI labels (possibly for an application like Facebook)

    oai_token-act-pair · gemini-2.0-flash

    dili

    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
    BASEPATH
    -0.51
    Duration
    -0.46
    ular
    -0.45
     tra
    -0.44
     ABC
    -0.43
     duration
    -0.42
     Duration
    -0.42
    <h2>
    -0.42
     j
    -0.41
     timing
    -0.41
    POSITIVE LOGITS
    省市镇
    0.78
     חיצוניים
    0.77
     שוליים
    0.74
    enumi
    0.73
    CloseOperation
    0.73
    tagHelperRunner
    0.71
    LabelTagHelper
    0.69
     unknownFields
    0.68
    enumii
    0.68
    脚注の使い方
    0.67
    Activations Density 21.071%

    No Known Activations