© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14092
    Prev
    Next
    INDEX
    Explanations

    language relevant to the American Civil War, particularly focusing on violence and strong opinions of the era.

    oai_token-act-pair · gemini-2.0-flash

    American history and slavery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     cervello
    -0.50
    WireFormatLite
    -0.48
     écrans
    -0.46
     légère
    -0.43
     taglio
    -0.42
    zsche
    -0.41
    InputTagHelper
    -0.40
     calificación
    -0.40
    uminen
    -0.39
    цездатний
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.78
    Referencie
    0.61
    JvmStatic
    0.61
     onCancelled
    0.59
    mobileqq
    0.58
    writeFieldEnd
    0.58
    ant
    0.57
    ۣ
    0.57
    endregion
    0.57
    ContentAsync
    0.56
    Activations Density 9.123%

    No Known Activations