© 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. 13548
    Prev
    Next
    INDEX
    Explanations

    statistical analysis results and measures of validity, reliability, sensitivity, and specificity

    oai_token-act-pair · gemini-2.0-flash

    8 and 9

    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
     typelib
    -0.81
    EndInit
    -0.67
     doInBackground
    -0.64
    DockStyle
    -0.57
    IsContent
    -0.56
     NgModule
    -0.56
    はじめに
    -0.53
     immédi
    -0.53
     AttributeSet
    -0.52
     sauvages
    -0.51
    POSITIVE LOGITS
    9
    0.90
    8
    0.88
    7
    0.80
     ninety
    0.71
     eighty
    0.69
     Ninety
    0.68
     eighties
    0.65
     seventy
    0.65
     seventies
    0.60
     Eighty
    0.59
    Activations Density 4.241%

    No Known Activations