© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    positive adjectives which often follow 'perfect'

    oai_token-act-pair · gemini-2.0-flash

    perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     perfect
    -2.44
    perfect
    -2.36
    Perfect
    -2.25
     Perfect
    -2.17
     PERFECT
    -1.91
     perfecto
    -1.70
     perfecta
    -1.67
     perfetto
    -1.63
    PERFECT
    -1.62
     perfe
    -1.59
    POSITIVE LOGITS
    NUMX
    0.72
    ươi
    0.63
    PointSize
    0.57
    ulx
    0.57
    IONAL
    0.57
    uvre
    0.56
    unanje
    0.56
     quoi
    0.55
    phazard
    0.55
    odb
    0.52
    Activations Density 1.127%

    No Known Activations