© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11575
    Prev
    Next
    INDEX
    Explanations

    adjectives or descriptive phrases and related words depending on the document being reviewed

    oai_token-act-pair · gemini-2.0-flash

    phrases or words in different languages

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ujednoznacz
    -0.81
    oader
    -0.80
    脚注の使い方
    -0.75
    లాలు
    -0.74
     AssemblyCulture
    -0.72
    ChildScrollView
    -0.72
     pinulongan
    -0.70
     estekak
    -0.70
    Personendaten
    -0.68
    CppMethod
    -0.66
    POSITIVE LOGITS
    lossenen
    0.42
     tiểu
    0.42
     PyTuple
    0.42
    注意事项
    0.40
    Chú
    0.40
     account
    0.40
    NameInMap
    0.40
     dense
    0.40
    깐
    0.39
    äf
    0.39
    Activations Density 0.850%

    No Known Activations