© 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. 9475
    Prev
    Next
    INDEX
    Explanations

    the word "somewhat", sometimes in proximity to sports or software development

    oai_token-act-pair · gemini-2.0-flash

    somewhat

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.00
    :✨
    -1.00
    GEBURTSDATUM
    -0.97
     RIPRODUZIONE
    -0.94
     propOrder
    -0.94
     romain
    -0.89
     ویکی‌پدی
    -0.88
     venons
    -0.87
     ainfi
    -0.84
    berdayakan
    -0.82
    POSITIVE LOGITS
    1
    0.74
    <b>
    0.72
    ’
    0.71
    7
    0.68
    8
    0.68
    2
    0.68
    5
    0.67
    “
    0.67
    9
    0.66
    <strong>
    0.65
    Activations Density 1.722%

    No Known Activations