© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2857
    Prev
    Next
    INDEX
    Explanations

    words and phrases that provide information or guide decision making

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    /**/*.
    -0.54
     '\\;'
    -0.52
     发表于
    -0.50
    enderror
    -0.50
    براير
    -0.50
    ecute
    -0.46
    elakaan
    -0.45
    سطس
    -0.45
    
    -0.43
    țial
    -0.43
    POSITIVE LOGITS
     this
    2.55
    this
    2.22
    This
    1.63
     This
    1.55
     denna
    1.55
     questa
    1.52
     THIS
    1.50
     questo
    1.49
     этого
    1.46
     dieses
    1.44
    Activations Density 2.661%

    No Known Activations