© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10920
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and sentence structures that indicate a scientific or technical context, often involving comparisons, results, and conclusions.

    oai_token-act-pair · gemini-2.0-flash

    increase or decrease

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    yon
    -0.43
    esModule
    -0.41
    YEN
    -0.41
     zuge
    -0.41
    zna
    -0.40
    Occ
    -0.40
    Cpp
    -0.39
    NDICE
    -0.39
    採
    -0.38
    lå
    -0.37
    POSITIVE LOGITS
     increase
    1.86
    increase
    1.71
     Increase
    1.64
     decrease
    1.63
     increases
    1.63
     increased
    1.62
    Increase
    1.62
     INCREASE
    1.55
    increases
    1.53
    increased
    1.52
    Activations Density 5.389%

    No Known Activations