© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4327
    Prev
    Next
    INDEX
    Explanations

    words and phrases that end with "ive", and also a few words that end in "ices" or "ishes", and also the phrase "advantage of the".

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     town
    -0.47
     kesi
    -0.45
    PickerController
    -0.41
     stranded
    -0.40
    Activités
    -0.40
     intention
    -0.39
    cticut
    -0.39
     billion
    -0.39
     Kir
    -0.38
    KSI
    -0.38
    POSITIVE LOGITS
     enjoying
    1.10
     enjoyed
    1.09
     enjoy
    1.08
     Enjoy
    1.07
    enjoy
    1.05
     ENJOY
    1.05
    Enjoy
    1.04
    Enjoying
    1.03
     enjoys
    1.01
    ENJOY
    0.94
    Activations Density 0.604%

    No Known Activations