© 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. 14970
    Prev
    Next
    INDEX
    Explanations

    positive superlatives and the words around them

    oai_token-act-pair · gemini-2.0-flash

    positive reviews

    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
     lenker
    -0.83
    TagMode
    -0.81
     ſeveral
    -0.78
     houſe
    -0.75
     leaſt
    -0.74
     Houſe
    -0.72
     bezeichneter
    -0.71
     Monfieur
    -0.71
    __(/*!
    -0.70
    Hochspringen
    -0.69
    POSITIVE LOGITS
     works
    0.68
    works
    0.50
     WORKS
    0.49
     ше
    0.48
    zep
    0.47
     Works
    0.47
    NSYLVANIA
    0.46
     anastom
    0.45
     Gazetteer
    0.45
     orgas
    0.45
    Activations Density 1.255%

    No Known Activations