© 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. 4997
    Prev
    Next
    INDEX
    Explanations

    words related to architecture and building materials

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding elements

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

    technical and architectural descriptions

    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
     NSCoder
    -0.62
    argout
    -0.61
    出版年
    -0.60
    AutoScale
    -0.60
    sipasi
    -0.59
     BorderRadius
    -0.59
    ngdoc
    -0.58
    colha
    -0.57
     eventdata
    -0.56
     manifestazione
    -0.56
    POSITIVE LOGITS
    FileDescriptor
    0.57
    extAlignment
    0.52
    RenderAtEndOf
    0.50
     Kese
    0.46
     Yaz
    0.46
    chel
    0.45
    epr
    0.45
    tagHelperRunner
    0.44
     progra
    0.44
     hack
    0.43
    Activations Density 0.498%

    No Known Activations