© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2268
    Prev
    Next
    INDEX
    Explanations

    a set of common words having to do with politics, time, computer science/research, and socioeconomic status in a manner that is difficult to describe generally.

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     situation
    -0.67
     series
    -0.60
     function
    -0.59
     division
    -0.57
     aspect
    -0.56
     terms
    -0.55
     agreement
    -0.54
     scene
    -0.53
     of
    -0.52
     factors
    -0.52
    POSITIVE LOGITS
    AndEndTag
    1.10
    berdayakan
    0.82
     traités
    0.79
     avoient
    0.77
     chrétiens
    0.75
     fédé
    0.75
     chrétien
    0.74
    AddTagHelper
    0.74
     disparu
    0.73
     étoient
    0.72
    Activations Density 4.053%

    No Known Activations