© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10369
    Prev
    Next
    INDEX
    Explanations

    subjective words describing the difficulty or simplicity of something

    oai_token-act-pair · gemini-2.0-flash

    difficulty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    NameInMap
    -0.79
    الإنجليزية
    -0.77
    原始内容存档于
    -0.71
     resourceCulture
    -0.62
     okuyayım
    -0.60
    GEBURTSDATUM
    -0.59
     kasarigan
    -0.57
    GEBURTS
    -0.56
    BeginInit
    -0.54
     Приступљено
    -0.54
    POSITIVE LOGITS
     to
    1.65
    to
    0.85
    ToRead
    0.77
     να
    0.76
    ToAdd
    0.74
    ToLoad
    0.73
    ToBe
    0.68
    tobe
    0.66
    ToSend
    0.66
     To
    0.64
    Activations Density 0.841%

    No Known Activations