© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7176
    Prev
    Next
    INDEX
    Explanations

    words related to offering, seeing, or certainty

    oai_token-act-pair · gemini-2.0-flash

    say "no"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     little
    -2.30
    little
    -2.17
    Little
    -1.79
     LITTLE
    -1.71
     Little
    -1.66
    LITTLE
    -1.54
     minimal
    -1.52
     peu
    -1.41
    minimal
    -1.39
     poco
    -1.38
    POSITIVE LOGITS
    zieży
    0.73
     AssemblyCulture
    0.73
    addCriterion
    0.59
    fromnode
    0.58
     فريبيس
    0.58
    rsiniz
    0.58
     NSCoder
    0.57
    RTGC
    0.57
    enumi
    0.57
    uesia
    0.56
    Activations Density 0.877%

    No Known Activations