© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15089
    Prev
    Next
    INDEX
    Explanations

    capitalized prefixes followed by parts of names or words

    oai_token-act-pair · gemini-2.0-flash

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     &___
    -0.49
    więcej
    -0.41
    <eos>
    -0.41
     Key
    -0.40
    えている
    -0.40
    えています
    -0.39
     unlike
    -0.39
    ke
    -0.39
    audi
    -0.39
     er
    -0.38
    POSITIVE LOGITS
     resourceCulture
    0.99
    Personendaten
    0.92
    parsedMessage
    0.87
     ISNI
    0.84
    BeginContext
    0.83
    bootstrapcdn
    0.82
     AspNetCore
    0.78
    IVEREF
    0.78
    Personensuche
    0.77
    invokeLater
    0.77
    Activations Density 0.208%

    No Known Activations