© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15103
    Prev
    Next
    INDEX
    Explanations

    code blocks and HTML elements that are closing

    oai_token-act-pair · gemini-2.0-flash

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -0.83
     viata
    -0.65
     abbraccio
    -0.60
     wikipagina
    -0.59
     abenço
    -0.59
     charité
    -0.57
    queryInterface
    -0.57
    feof
    -0.57
     Comprometido
    -0.56
    الحياه
    -0.56
    POSITIVE LOGITS
    setVerticalGroup
    0.72
    VIAF
    0.67
    __":
    0.64
    EndGlobalSection
    0.59
    __':
    0.58
    StoryboardSegue
    0.58
    |}{}
    0.57
     VIAF
    0.57
    ">//
    0.55
    رسد
    0.55
    Activations Density 1.510%

    No Known Activations