© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2426
    Prev
    Next
    INDEX
    Explanations

    legal case documents, or version release notes

    oai_token-act-pair · gemini-2.0-flash

    legal/code document

    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
     cuadrados
    -0.46
    List
    -0.43
    mark
    -0.42
    整
    -0.40
    <bos>
    -0.40
    get
    -0.40
     
    -0.38
    ini
    -0.38
    ir
    -0.37
    U
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    1.12
     שוליים
    1.05
     للاسماء
    0.90
     GenerationType
    0.90
    CodeAttribute
    0.89
     snippetHide
    0.88
    StoryboardSegue
    0.84
    出版年
    0.84
    BASEPATH
    0.83
    WriteTagHelper
    0.82
    Activations Density 3.433%

    No Known Activations