© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    a wide variety of unrelated topics

    oai_token-act-pair · gemini-2.0-flash

    Internet content

    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
     EconPapers
    -0.65
     resourceCulture
    -0.65
    Sucesor
    -0.59
    RenderAtEndOf
    -0.57
     createSprite
    -0.55
    WithIOException
    -0.55
    SequentialGroup
    -0.53
    oneofs
    -0.52
    EnableWeb
    -0.52
     يتيمه
    -0.51
    POSITIVE LOGITS
     بيها
    0.75
     machine
    0.61
     train
    0.57
    iNdEx
    0.55
     mine
    0.54
    shund
    0.52
     MACHINE
    0.52
    chestra
    0.49
     Machine
    0.48
    machine
    0.48
    Activations Density 3.873%

    No Known Activations