© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9388
    Prev
    Next
    INDEX
    Explanations

    words that introduce, qualify, or describe a fact, study, or belief.

    oai_token-act-pair · gemini-2.0-flash

    adverbs of frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Италијани
    -0.52
    featureID
    -0.50
    DialogInterface
    -0.47
     своего
    -0.46
    Hentet
    -0.45
    ьаж
    -0.45
    存于互联网档案馆
    -0.44
    penet
    -0.43
     químicas
    -0.42
    IsPostBack
    -0.42
    POSITIVE LOGITS
    <bos>
    0.89
    はじめに
    0.70
    \{\\
    0.66
    atoire
    0.65
     poffible
    0.64
     againſt
    0.64
    المكان
    0.63
     becauſe
    0.60
     myſelf
    0.60
     vectorstock
    0.59
    Activations Density 8.078%

    No Known Activations