© 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. 12370
    Prev
    Next
    INDEX
    Explanations

    words that are verbs or verb-like within computer code and/or non-English text

    oai_token-act-pair · gemini-2.0-flash

    Conversations

    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
    Negative Logits
     constantly
    -0.71
     continual
    -0.67
     continually
    -0.64
     constantemente
    -0.63
     chodzi
    -0.62
     fazia
    -0.60
     constant
    -0.59
    saraba
    -0.59
     sürekli
    -0.58
     castelo
    -0.57
    POSITIVE LOGITS
    σουμε
    0.73
     Ressource
    0.59
    Geplaatst
    0.57
     again
    0.55
    σουν
    0.53
    consulté
    0.53
     Levine
    0.52
     Dicapai
    0.52
     dàng
    0.52
     emergencia
    0.52
    Activations Density 8.130%

    No Known Activations