© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3953
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to preparing and eating high-quality tomato dishes

    oai_token-act-pair · gemini-2.0-flash

    programming code elements and terms

    np_token-act-pair-logits · gpt-4o-mini

    food ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ciamo
    -0.51
    fires
    -0.50
    Espèce
    -0.49
     fires
    -0.47
    Жизнь
    -0.45
    nocześnie
    -0.45
     Clippers
    -0.44
     Fires
    -0.44
    cplusplus
    -0.43
    ocarcinoma
    -0.43
    POSITIVE LOGITS
     ExecuteAsync
    0.73
    ReusableCell
    0.65
     AssemblyCulture
    0.63
    enumi
    0.58
     CreateTagHelper
    0.55
     محفوظة
    0.54
    GTCX
    0.52
     kasarigan
    0.52
    istoitu
    0.51
    cí
    0.50
    Activations Density 1.428%

    No Known Activations