© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4042
    Prev
    Next
    INDEX
    Explanations

    names of theatrical plays, awards, and playwrights

    oai_token-act-pair · gemini-2.0-flash

    plays and theater

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     expulsion
    -0.53
     BoxFit
    -0.51
     expel
    -0.50
    npos
    -0.49
    balleur
    -0.49
     venons
    -0.48
     soundtrack
    -0.48
     Soundtrack
    -0.48
     remix
    -0.48
    amzn
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.89
    fillType
    0.73
    GEBURTSDATUM
    0.71
    basicConfig
    0.69
    EndProject
    0.68
    osoba
    0.65
    참고
    0.64
     CreateTagHelper
    0.64
    withCredentials
    0.59
    مصادر
    0.57
    Activations Density 0.177%

    No Known Activations