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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 657
    Prev
    Next
    INDEX
    Explanations

    mentions of place names in the American South, particularly locations in North Carolina and Tennessee

    oai_token-act-pair · gemini-2.0-flash

    cities and areas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    KommentareTeilen
    -0.73
     Мексичка
    -0.65
     @"/
    -0.63
    tanleria
    -0.60
     bezeichneter
    -0.59
     насељу
    -0.59
    Trama
    -0.57
    asuring
    -0.57
    msgTypes
    -0.54
    URLException
    -0.54
    POSITIVE LOGITS
     électriques
    0.51
     financières
    0.49
     darah
    0.49
    thoff
    0.49
     européennes
    0.47
    js
    0.47
     eléctricos
    0.47
     víz
    0.46
     anggaran
    0.46
    loxy
    0.46
    Activations Density 3.579%

    No Known Activations