© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12118
    Prev
    Next
    INDEX
    Explanations

    the word "good" and associated sentiment oriented words around it, such as "news"

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    good
    -0.74
     Good
    -0.72
    Good
    -0.71
     good
    -0.69
     GOOD
    -0.67
    GOOD
    -0.62
     buenas
    -0.59
     fallu
    -0.57
     bonne
    -0.56
     buenos
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.97
    TagMode
    0.74
    PhysRevD
    0.73
    ScopeManager
    0.72
    ConstraintMaker
    0.67
    contentLoaded
    0.66
    reportWebVitals
    0.63
    endphp
    0.63
    énario
    0.63
    Viited
    0.62
    Activations Density 8.790%

    No Known Activations