© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5005
    Prev
    Next
    INDEX
    Explanations

    adulatory words, especially those implying someone is great

    oai_token-act-pair · gemini-2.0-flash

    strong positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -0.72
    xtext
    -0.56
    moveToFirst
    -0.55
     ***!
    -0.49
    اظ
    -0.49
    <bos>
    -0.49
    мости
    -0.48
     East
    -0.47
    ngan
    -0.46
    EventData
    -0.46
    POSITIVE LOGITS
    DebuggerStep
    0.64
     AssemblyCompany
    0.64
     ſy
    0.60
    mybatisplus
    0.59
     schwä
    0.59
     Majefty
    0.58
     Jefus
    0.58
     Theſe
    0.58
    ftagPool
    0.57
     Connectez
    0.56
    Activations Density 1.909%

    No Known Activations