© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13532
    Prev
    Next
    INDEX
    Explanations

    words and phrases from a variety of domains seemingly related to requirements and constraints

    oai_token-act-pair · gemini-2.0-flash

    Technical services/groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    sizeCache
    -0.75
     الدولى
    -0.65
    AnimationsModule
    -0.65
     EconPapers
    -0.64
    onViewCreated
    -0.63
    ◗
    -0.63
    thâu
    -0.61
    AutoScaleMode
    -0.61
    Filmografie
    -0.60
    理石
    -0.60
    POSITIVE LOGITS
     calendriers
    0.51
     whilst
    0.50
     Landwir
    0.48
     now
    0.46
    ölk
    0.45
    altung
    0.42
     soutenu
    0.41
     Whilst
    0.41
    agliari
    0.41
    Whilst
    0.41
    Activations Density 0.701%

    No Known Activations