© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7759
    Prev
    Next
    INDEX
    Explanations

    references to unusual things, especially when described using prepositions

    oai_token-act-pair · gemini-2.0-flash

    wheels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ways
    -0.89
     maneiras
    -0.73
     WAYS
    -0.67
     lenker
    -0.65
     Ways
    -0.65
     дописавши
    -0.64
    WriteTagHelper
    -0.63
    MigrationBuilder
    -0.62
     manières
    -0.62
     وتسجيلات
    -0.61
    POSITIVE LOGITS
     wheels
    0.93
     Wheels
    0.77
    wheels
    0.68
    fromCharCode
    0.61
     wings
    0.61
     WHE
    0.58
    Wheels
    0.58
    Rohy
    0.56
     wheeled
    0.55
     Wings
    0.53
    Activations Density 0.616%

    No Known Activations