© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    outdoor, musical events with a seasonal or geographic association

    oai_token-act-pair · gemini-2.0-flash

    events and festivals

    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
    extAlignment
    -0.79
     resourceCulture
    -0.71
     MaterialApp
    -0.65
    aarrggbb
    -0.61
     referenties
    -0.60
    IsContent
    -0.56
     viewType
    -0.55
     tắt
    -0.54
    bootstrapcdn
    -0.54
     оригіналу
    -0.52
    POSITIVE LOGITS
    lüssel
    0.59
     esterna
    0.54
     vibrate
    0.54
     humaines
    0.52
     =>'
    0.50
     juridiques
    0.50
     humanidad
    0.50
     hidupnya
    0.49
     erw
    0.49
     humains
    0.49
    Activations Density 0.404%

    No Known Activations