© 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. 5435
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to processes, equipment, physical systems, and facilities

    oai_token-act-pair · gemini-2.0-flash

    specialized software-related terms

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

    equipment

    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
    ivably
    -0.46
    PyExc
    -0.46
    Siddhartha
    -0.45
    oredCriteria
    -0.43
    ADELPHIA
    -0.43
     UITextField
    -0.40
    elemField
    -0.39
    */),
    -0.39
    arResult
    -0.39
     StringField
    -0.39
    POSITIVE LOGITS
     onCreateView
    0.63
     giáp
    0.59
     consumed
    0.57
     שוליים
    0.56
    rítica
    0.56
    kontroll
    0.56
    iade
    0.55
     grecque
    0.55
    chetto
    0.55
     noires
    0.55
    Activations Density 5.809%

    No Known Activations