© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8378
    Prev
    Next
    INDEX
    Explanations

    the phrase "along the way"

    oai_token-act-pair · gemini-2.0-flash

    say "the" or "way"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ste
    -0.49
     path
    -0.46
    Ste
    -0.45
    влечения
    -0.44
    Path
    -0.44
    path
    -0.44
     along
    -0.44
    üyor
    -0.44
     Path
    -0.43
     organes
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
    InjectAttribute
    0.85
     дописавши
    0.79
     nahilalakip
    0.76
    afficheront
    0.76
     مشين
    0.73
     CreateTagHelper
    0.72
    SharedDtor
    0.70
    EndGlobalSection
    0.69
    IntoConstraints
    0.68
    Activations Density 1.157%

    No Known Activations