© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    the word "On" indicating the start of a sentence or a description of something happening

    oai_token-act-pair · gemini-2.0-flash

    On

    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
     On
    -1.56
    On
    -1.14
     ON
    -1.05
    nasium
    -0.83
    ON
    -0.81
    Personendaten
    -0.81
    Personensuche
    -0.79
     unknownFields
    -0.78
    }%
    -0.76
     ExecuteAsync
    -0.75
    POSITIVE LOGITS
    <bos>
    0.81
     on
    0.76
    For
    0.59
     dessous
    0.56
    for
    0.52
    ^{
    0.52
     по
    0.51
    '
    0.51
     на
    0.49
     the
    0.49
    Activations Density 0.388%

    No Known Activations