© 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. 6929
    Prev
    Next
    INDEX
    Explanations

    words related to food, drink, and travelling

    oai_token-act-pair · gemini-2.0-flash

    wine, beer

    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
     estekak
    -0.71
    Javadoc
    -0.58
     AssemblyVersion
    -0.55
     незавершена
    -0.53
    הערות
    -0.49
     bonté
    -0.49
    MENAFN
    -0.49
    WithFormat
    -0.48
    Спасылкі
    -0.48
     copias
    -0.48
    POSITIVE LOGITS
     jadx
    0.49
    HasColumnType
    0.48
     quanto
    0.48
    NOPQRST
    0.47
    iata
    0.47
    GetAsync
    0.46
    iaire
    0.46
    ukone
    0.45
    fontein
    0.44
     baga
    0.44
    Activations Density 0.570%

    No Known Activations