© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5785
    Prev
    Next
    INDEX
    Explanations

    the syntax of several programming languages

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    oredCriteria
    -0.92
     worldly
    -0.88
    ########.
    -0.82
    +#+#
    -0.79
    worldly
    -0.79
    出版年
    -0.76
     للمعارف
    -0.75
    seamnă
    -0.73
     world
    -0.68
     Мексичка
    -0.67
    POSITIVE LOGITS
    QtWidgets
    0.44
    Referenties
    0.42
    )(
    0.42
    REFER
    0.40
     operation
    0.40
     nost
    0.39
    操作
    0.39
    ）（
    0.38
     IP
    0.38
    <eos>
    0.38
    Activations Density 2.198%

    No Known Activations