© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    code diffs and quoted speech.

    oai_token-act-pair · gemini-2.0-flash

    Code and quotes

    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
    ValueStyle
    -0.68
    adaptiveStyles
    -0.66
    XmlAccessType
    -0.64
    bootstrapcdn
    -0.61
    ValueGeneration
    -0.59
    espèce
    -0.59
    最快更新
    -0.59
    ffine
    -0.58
    CodeDom
    -0.57
     RVA
    -0.57
    POSITIVE LOGITS
    stool
    0.47
     who
    0.47
     Sel
    0.45
    <bos>
    0.45
     Cle
    0.43
    iker
    0.43
     Kons
    0.43
    omorphism
    0.43
    mola
    0.42
    clique
    0.42
    Activations Density 0.895%

    No Known Activations