© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3925
    Prev
    Next
    INDEX
    Explanations

    mentions of ships and disasters, especially geographically specific ones

    oai_token-act-pair · gemini-2.0-flash

    sea, coast, water

    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
     sea
    -2.25
     Sea
    -2.17
     ocean
    -2.13
     Ocean
    -2.11
    Sea
    -2.03
     coastal
    -1.99
    Ocean
    -1.98
     Coastal
    -1.91
    sea
    -1.91
     beach
    -1.90
    POSITIVE LOGITS
    ்ச
    0.57
    OuterClass
    0.57
    SBATCH
    0.54
    EndGlobalSection
    0.50
     Normdatei
    0.49
    SpringRunner
    0.47
     django
    0.47
     Wiseman
    0.46
    protoc
    0.46
     waard
    0.44
    Activations Density 1.367%

    No Known Activations