© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to satellite navigation devices

    oai_token-act-pair · gemini-2.0-flash

    GPS and mapping

    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
     map
    -1.02
     maps
    -0.98
     Maps
    -0.90
     GPS
    -0.85
     Map
    -0.84
    Maps
    -0.80
    Map
    -0.79
    map
    -0.78
    maps
    -0.76
    GPS
    -0.76
    POSITIVE LOGITS
     lenker
    0.56
    ectoria
    0.54
     المرجع
    0.52
     gekomen
    0.52
    uyez
    0.50
    TestBed
    0.49
    >//
    0.47
    unknownFields
    0.47
     HasFactory
    0.47
    Karriere
    0.47
    Activations Density 2.439%

    No Known Activations