© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4064
    Prev
    Next
    INDEX
    Explanations

    references to Boeing 747 aircraft and related terms like "jet transport"

    oai_token-act-pair · gemini-2.0-flash

    Aviation/air travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     purpoſe
    -0.65
     themſelves
    -0.64
    Архівовано
    -0.62
     Saline
    -0.62
    rítica
    -0.61
     Rueda
    -0.60
    šanai
    -0.60
    MediaStore
    -0.59
    anskje
    -0.59
    openzeppelin
    -0.59
    POSITIVE LOGITS
    исленность
    0.49
    вин
    0.47
    ime
    0.46
    }],
    0.46
    vie
    0.46
    posedge
    0.43
    Traceback
    0.42
    noin
    0.42
    脚注の使い方
    0.41
    ‎
    0.41
    Activations Density 0.389%

    No Known Activations