© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3175
    Prev
    Next
    INDEX
    Explanations

    words that are not nouns and that are next to punctuation

    oai_token-act-pair · gemini-2.0-flash

    Academic publications

    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
    VIAF
    -0.51
     Western
    -0.46
    openqa
    -0.45
    ươ
    -0.44
     cache
    -0.42
    opot
    -0.41
    EndGlobalSection
    -0.39
    IMPORTED
    -0.38
     '{@
    -0.38
     nakalista
    -0.37
    POSITIVE LOGITS
     препратки
    0.77
    Tikang
    0.73
    Personendaten
    0.65
    Indented
    0.60
     >=",
    0.60
     préférence
    0.59
    AccessorTable
    0.58
     تضيفلها
    0.57
     storici
    0.57
     Réponses
    0.56
    Activations Density 2.476%

    No Known Activations