© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    words and phrases that present a logical argument or justification

    oai_token-act-pair · gemini-2.0-flash

    causality and consequence

    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
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.48
    <bos>
    -0.47
    
    -0.43
    /******/
    -0.42
    PyTuple
    -0.41
     становника
    -0.41
    出版年
    -0.41
    ThemeProvider
    -0.40
     D
    -0.39
     Al
    -0.39
    POSITIVE LOGITS
     purpoſe
    0.77
     houſe
    0.74
     ſtate
    0.66
     Houſe
    0.65
     uſed
    0.65
     pleaſure
    0.65
     poffe
    0.63
     Perſ
    0.62
     reaſon
    0.62
     ſhe
    0.62
    Activations Density 3.828%

    No Known Activations