© 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. 2511
    Prev
    Next
    INDEX
    Explanations

    intensifiers or words that emphasize a feeling or adjective

    oai_token-act-pair · gemini-2.0-flash

    emphasis

    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
     ModelExpression
    -1.07
    rungsseite
    -0.94
     oprot
    -0.87
    
    -0.85
     noDo
    -0.84
    MigrationBuilder
    -0.84
    GEBURTSDATUM
    -0.82
    SourceChecksum
    -0.81
    الإنجليزية
    -0.81
     >=",
    -0.80
    POSITIVE LOGITS
     very
    0.78
     incredibly
    0.68
     extremely
    0.66
    非常
    0.63
     great
    0.60
     VERY
    0.59
     amazingly
    0.57
    very
    0.56
     amazing
    0.56
     Very
    0.55
    Activations Density 0.830%

    No Known Activations