© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10130
    Prev
    Next
    INDEX
    Explanations

    text about the New York Giants football team

    oai_token-act-pair · gemini-2.0-flash

    sports news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Col
    -0.45
    gle
    -0.45
    Cha
    -0.44
    aret
    -0.44
    bewerken
    -0.44
    gg
    -0.42
    Gim
    -0.42
    Phaser
    -0.41
     MEASURE
    -0.41
     remise
    -0.40
    POSITIVE LOGITS
    rrggbb
    0.72
     AssemblyCulture
    0.72
     nakalista
    0.70
    apunov
    0.69
    CodeAttribute
    0.69
    تقاوى
    0.67
     VIAF
    0.66
    ANTLR
    0.65
    prepareStatement
    0.63
    DoubleQuotes
    0.60
    Activations Density 1.563%

    No Known Activations