© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12164
    Prev
    Next
    INDEX
    Explanations

    the root form of the verb "get" and words with similar meanings like find, run, and hurdle

    oai_token-act-pair · gemini-2.0-flash

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    styleType
    -1.03
     get
    -0.87
    get
    -0.72
     getting
    -0.70
     gets
    -0.70
    AnimationsModule
    -0.68
    onomía
    -0.67
    GetKeyDown
    -0.66
     Get
    -0.66
    IsContent
    -0.65
    POSITIVE LOGITS
    expandindo
    0.74
    Referències
    0.59
    まま
    0.56
     magnética
    0.52
    köy
    0.49
    cipy
    0.49
     violenta
    0.48
    +:+
    0.46
     lágrimas
    0.46
    ágok
    0.45
    Activations Density 0.124%

    No Known Activations