© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    opinionated language and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     Similar
    -0.54
     similar
    -0.50
     δο
    -0.48
    formazione
    -0.46
    mismo
    -0.46
    similar
    -0.45
    Similar
    -0.44
     كومونز
    -0.44
    same
    -0.44
    formazioni
    -0.44
    POSITIVE LOGITS
     beginnetje
    0.80
    SpringBootTest
    0.77
    AnimationsModule
    0.69
     TextInputType
    0.68
    KEYCODE
    0.67
     AssemblyCulture
    0.67
    mybatisplus
    0.65
    RunAsync
    0.64
     مرئيه
    0.63
    GEBURTSDATUM
    0.62
    Activations Density 1.586%

    No Known Activations