© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12783
    Prev
    Next
    INDEX
    Explanations

    phrases related to persisting or choosing a course of action and sticking to it

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     kasarigan
    -0.69
    mampuan
    -0.65
    หว่าง
    -0.64
     يتيمه
    -0.63
     createState
    -0.59
    FontOfSize
    -0.58
    #+#
    -0.58
    kháu
    -0.57
    حياته
    -0.56
    hadiran
    -0.56
    POSITIVE LOGITS
     adhere
    0.63
     adhered
    0.62
     adherence
    0.57
     stick
    0.55
     adhering
    0.54
     adheres
    0.54
     sticks
    0.53
    GraphicsUnit
    0.52
     बज
    0.52
    keep
    0.49
    Activations Density 1.640%

    No Known Activations