© 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. 14699
    Prev
    Next
    INDEX
    Explanations

    text discussing railroad crossings, trains, and safety

    oai_token-act-pair · gemini-2.0-flash

    trains

    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
     rail
    -1.99
     Rail
    -1.92
     train
    -1.92
    Rail
    -1.91
     RAIL
    -1.85
     Train
    -1.84
     railway
    -1.84
     Trains
    -1.79
     trains
    -1.79
    rail
    -1.77
    POSITIVE LOGITS
    綜合報導
    0.49
     JSON
    0.47
     Perez
    0.46
     bite
    0.45
     Novgorod
    0.45
     Erica
    0.44
    Perez
    0.43
     Kyle
    0.43
     Nathan
    0.42
    Brittany
    0.42
    Activations Density 1.315%

    No Known Activations