© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    a variety of language constructs, including HTML/code snippets, question/answer sequences, and legal/official correspondence

    oai_token-act-pair · gemini-2.0-flash

    response

    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
    GEBURTSDATUM
    -0.75
     nahilalakip
    -0.73
    principalColumn
    -0.66
    __':
    -0.65
    ReadInt
    -0.63
    Dış
    -0.63
     propOrder
    -0.63
    CPtr
    -0.62
     AssemblyVersion
    -0.61
    ftagPool
    -0.60
    POSITIVE LOGITS
     response
    1.49
    response
    1.24
     responses
    1.23
     reply
    1.23
     respond
    1.22
     Response
    1.19
     responds
    1.10
     réponse
    1.10
     RESPONSE
    1.09
     answer
    1.08
    Activations Density 2.632%

    No Known Activations