© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7206
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and context associated with strong, potentially negative opinions or intense dialogue within a narrative

    oai_token-act-pair · gemini-2.0-flash

    Dialogue and discussion

    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
     otomatig
    -0.93
    principalColumn
    -0.91
    HasForeignKey
    -0.80
    TagMode
    -0.75
    Ecotoxicity
    -0.74
    
    -0.73
     calendriers
    -0.72
     المعيارى
    -0.71
    ViewImports
    -0.70
     utafitiHapana
    -0.70
    POSITIVE LOGITS
     exposition
    0.53
     statement
    0.52
     scene
    0.52
     speech
    0.50
     discussion
    0.50
     dialogue
    0.49
    説
    0.48
    rapid
    0.48
    説明
    0.47
    scene
    0.47
    Activations Density 6.555%

    No Known Activations