© 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. 12211
    Prev
    Next
    INDEX
    Explanations

    words and phrases linked to the use of technology or resources for various purposes , whether for good or ill.

    oai_token-act-pair · gemini-2.0-flash

    Politics and technology

    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
     gainera
    -0.53
    ètre
    -0.52
     trần
    -0.51
    phylococcus
    -0.50
    Autoritní
    -0.49
    testens
    -0.48
    CIOS
    -0.47
    scriptcase
    -0.47
    っこう
    -0.47
     Audiodateien
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.63
     onBind
    0.55
    ThroughAttribute
    0.54
    awtextra
    0.52
    actylus
    0.50
    IsMutable
    0.50
    TintMode
    0.49
     InputDecoration
    0.48
    Сюжет
    0.48
     typelib
    0.47
    Activations Density 0.398%

    No Known Activations