© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9433
    Prev
    Next
    INDEX
    Explanations

    adjectives preceding a noun, often with an article

    oai_token-act-pair · gemini-2.0-flash

    Programming/Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TargetException
    -0.76
    TagMode
    -0.75
    ReusableCell
    -0.67
    HostException
    -0.65
    TestingModule
    -0.65
    WaitGroup
    -0.59
     محفوظة
    -0.57
    saga
    -0.56
     وتسجيلات
    -0.54
     MainAxisSize
    -0.53
    POSITIVE LOGITS
    SharedCtor
    0.56
    ьаж
    0.47
     marrone
    0.46
    zionato
    0.46
    Interface
    0.44
     surla
    0.43
    ÈME
    0.43
    viewBox
    0.42
     Ella
    0.41
     Antoine
    0.41
    Activations Density 2.821%

    No Known Activations