© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns relating to performing an action, or concepts of getting free from some impediment

    oai_token-act-pair · gemini-2.0-flash

    getting rid of something

    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
    DeleteBehavior
    -0.89
    PhysRevD
    -0.76
     ComVisible
    -0.68
    تقاوى
    -0.67
     ReactDOM
    -0.63
    Filmografie
    -0.63
    XmlAccessType
    -0.60
    равда
    -0.60
    !*\
    -0.58
    LLocation
    -0.58
    POSITIVE LOGITS
     }^{[
    0.57
    ल्स
    0.54
     honourable
    0.51
    anueva
    0.51
    _',
    0.50
    //[
    0.50
     niks
    0.50
     disregard
    0.50
     definitely
    0.49
     thingy
    0.49
    Activations Density 3.944%

    No Known Activations