© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    words indicating a change or restoration

    oai_token-act-pair · gemini-2.0-flash

    Restoring/changing/improving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -0.82
     Monfieur
    -0.80
     itſelf
    -0.74
     themſelves
    -0.73
     pleaſure
    -0.72
     himſelf
    -0.71
     ſeveral
    -0.66
     ſtill
    -0.65
     tartalomajánló
    -0.63
     Majefty
    -0.63
    POSITIVE LOGITS
     viewDidLoad
    0.55
     break
    0.54
    break
    0.46
    0.44
    MigrationBuilder
    0.44
     actionTypes
    0.44
    Chairs
    0.44
     invite
    0.44
     Shar
    0.43
    ayi
    0.43
    Activations Density 4.810%

    No Known Activations