© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13200
    Prev
    Next
    INDEX
    Explanations

    words describing specific cuisines, dishes, and ingredients

    oai_token-act-pair · gemini-2.0-flash

    food descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    setVerticalGroup
    -0.79
     omelette
    -0.73
     yolk
    -0.67
    ArgsConstructor
    -0.62
     Económica
    -0.61
     doInBackground
    -0.60
    CloseOperation
    -0.60
     BorderRadius
    -0.59
     ""],
    -0.59
     eggs
    -0.59
    POSITIVE LOGITS
    ніципа
    0.66
    Tikang
    0.54
    Distribuzione
    0.53
    inaw
    0.49
     دیکھیے
    0.48
    entennial
    0.48
     intptr
    0.45
    ۇ
    0.44
     Che
    0.43
     Caldwell
    0.43
    Activations Density 2.020%

    No Known Activations