© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13948
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to Visual Studio, interspersed with seemingly random HTML artifacts.

    oai_token-act-pair · gemini-2.0-flash

    Visual Studio, Wonder Woman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.61
    "
    -0.56
     Jurisdiction
    -0.53
    jdk
    -0.50
     grond
    -0.50
     sun
    -0.50
    滨
    -0.49
    ↵↵
    -0.48
    (
    -0.47
     jurisdiction
    -0.47
    POSITIVE LOGITS
     незавершена
    0.88
    ReusableCell
    0.75
     doubtnut
    0.73
     Efq
    0.71
    +:+
    0.69
     fhould
    0.68
    mybatisplus
    0.66
    ConstraintMaker
    0.66
    cipy
    0.66
    maketitle
    0.66
    Activations Density 0.820%

    No Known Activations