© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    references to legal documents and court cases

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pymongo
    -0.47
    umpulkan
    -0.45
    moor
    -0.44
    StoreMessageInfo
    -0.43
    PRNewswire
    -0.43
    égalité
    -0.42
    complexContent
    -0.42
    indépendance
    -0.41
    publicain
    -0.41
    йка
    -0.41
    POSITIVE LOGITS
     nôtre
    0.75
     Monfieur
    0.66
     appartamento
    0.65
     église
    0.65
     ainfi
    0.63
     alley
    0.62
     Majefty
    0.60
     eſt
    0.60
     aſ
    0.60
     houſe
    0.59
    Activations Density 14.252%

    No Known Activations