© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3286
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to find place names and specific locations while also being activated by some seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    ugd

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     EconPapers
    -0.85
    thâu
    -0.62
     насељу
    -0.59
    AnchorStyles
    -0.56
    ГЛА
    -0.52
    🔙
    -0.50
    Unmarshaller
    -0.50
    μφωνα
    -0.50
    ulemon
    -0.50
     AssemblyCompany
    -0.50
    POSITIVE LOGITS
     Vikipedi
    0.66
     BoxDecoration
    0.57
    rungsseite
    0.56
     &___
    0.55
     InputDecoration
    0.53
     bless
    0.52
    ">:
    0.51
     AssemblyProduct
    0.50
     Polda
    0.49
    GraphicsUnit
    0.48
    Activations Density 0.315%

    No Known Activations