© 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. 12576
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis, sports performance, politics and economics, technical problems, and gene silencing

    oai_token-act-pair · gemini-2.0-flash

    returning

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Recovery
    -1.14
     recovery
    -1.12
    Recovery
    -1.05
     recover
    -1.01
     RECOVERY
    -0.98
    recovery
    -0.95
     recovers
    -0.87
    Recover
    -0.86
     recovered
    -0.85
     recovering
    -0.85
    POSITIVE LOGITS
    featureID
    0.60
     ویکی‌پدیای
    0.52
    Datuak
    0.52
     raya
    0.51
    cjach
    0.49
     discarding
    0.48
     vrai
    0.47
     Einf
    0.47
    تقاوى
    0.47
     تضيفلها
    0.46
    Activations Density 33.128%

    No Known Activations