© 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. 14441
    Prev
    Next
    INDEX
    Explanations

    scientific terms and research activities, particularly in astrophysics and particle physics

    oai_token-act-pair · gemini-2.0-flash

    Stars

    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
     Efq
    -0.75
     Monfieur
    -0.70
     againſt
    -0.68
     itſelf
    -0.67
     Shakspeare
    -0.66
     tranſ
    -0.64
     ſta
    -0.63
     ſhe
    -0.63
     myſelf
    -0.63
    expandindo
    -0.62
    POSITIVE LOGITS
     stars
    0.74
     star
    0.62
    stars
    0.50
     Stars
    0.47
     STARS
    0.46
    星
    0.45
    assertRaises
    0.45
    ngOnInit
    0.45
     nakalista
    0.44
    مراجع
    0.44
    Activations Density 7.365%

    No Known Activations