© 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. 13494
    Prev
    Next
    INDEX
    Explanations

    words related to movement or directionality, especially when combined with prepositions or auxiliary verbs.

    oai_token-act-pair · gemini-2.0-flash

    jumping/lunging

    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
     jump
    -0.77
     jumped
    -0.77
     jumping
    -0.75
     Jumping
    -0.73
     leapt
    -0.72
    Jump
    -0.70
     Jump
    -0.69
     leaps
    -0.69
     leaped
    -0.69
     leaping
    -0.69
    POSITIVE LOGITS
     Normdatei
    0.64
    RoutingModule
    0.60
     MessageBoxIcon
    0.59
    TargetException
    0.58
     estekak
    0.58
    IUrlHelper
    0.58
     exacta
    0.54
    بوابة
    0.54
    siella
    0.52
    Portail
    0.50
    Activations Density 16.546%

    No Known Activations