© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15595
    Prev
    Next
    INDEX
    Explanations

    words that describe actions taken by people.

    oai_token-act-pair · gemini-2.0-flash

    pushing boundaries

    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
    Not in Any Lists

    No Comments

    Negative Logits
     push
    -1.28
     pushing
    -1.10
    push
    -1.10
     pushed
    -1.09
     pushes
    -1.07
     Push
    -1.06
    Push
    -1.05
     PUSH
    -0.96
     Pushing
    -0.93
    Pushing
    -0.92
    POSITIVE LOGITS
    ValueStyle
    0.75
    __':
    0.73
     مشين
    0.70
     kaynağından
    0.67
     smtplib
    0.66
     NgModule
    0.65
     onCreateView
    0.65
     BitmapFactory
    0.63
    InitStructure
    0.63
     fopen
    0.62
    Activations Density 42.669%

    No Known Activations