© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    the word "benefit", code parenthesis, dis- and olum-.

    oai_token-act-pair · gemini-2.0-flash

    benefit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     BoxFit
    -1.18
    endphp
    -0.96
    >--}}
    -0.96
     quelcon
    -0.94
    Cordialement
    -0.94
    AnchorStyles
    -0.94
     '{@
    -0.91
     كومونز
    -0.90
     AssemblyProduct
    -0.88
    المراجع
    -0.87
    POSITIVE LOGITS
    1
    0.73
    2
    0.69
    ↵
    0.65
    ↵↵
    0.59
    3
    0.55
    culable
    0.54
    He
    0.54
    [
    0.54
    4
    0.52
    0
    0.51
    Activations Density 1.392%

    No Known Activations