© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 8073
    Prev
    Next
    INDEX
    Explanations

    negative reviews or things that are important

    oai_token-act-pair · gemini-2.0-flash

    the word "to"

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

    "to" in other languages

    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
    WebVitals
    -0.81
    はじめに
    -0.73
     resourceCulture
    -0.58
    astify
    -0.57
    yelitis
    -0.56
    новниш
    -0.56
     通販
    -0.54
     BrowserModule
    -0.54
    <()>
    -0.54
     kasarigan
    -0.52
    POSITIVE LOGITS
     to
    2.38
     να
    1.11
    to
    0.91
     abzu
    0.79
     чтобы
    0.78
     aufzu
    0.75
    ที่จะ
    0.75
     להיות
    0.74
    tobe
    0.73
     auszu
    0.72
    Activations Density 1.927%

    No Known Activations