© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    the word "all", and sometimes numbers or words indicating inclusion or belonging.

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     all
    -0.57
    enski
    -0.54
     cons
    -0.54
     globally
    -0.52
     easily
    -0.52
     selv
    -0.51
     qu
    -0.50
     alla
    -0.48
     self
    -0.47
     either
    -0.47
    POSITIVE LOGITS
     Monfieur
    1.05
    IsContent
    0.98
     Efq
    0.97
     Italijanski
    0.90
    SequentialGroup
    0.86
     ainfi
    0.86
    OGND
    0.85
     feroit
    0.83
     EconPapers
    0.82
    RenderAtEndOf
    0.80
    Activations Density 6.749%

    No Known Activations