© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    place names, especially in a historical context

    oai_token-act-pair · gemini-2.0-flash

    kinds of rooms

    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
     sites
    -0.69
     Sites
    -0.63
    Sites
    -0.61
    GEBURTS
    -0.60
    Points
    -0.59
     points
    -0.58
    saraba
    -0.56
     SITES
    -0.55
     towns
    -0.55
    cities
    -0.54
    POSITIVE LOGITS
     offices
    0.95
     Offices
    0.88
     classrooms
    0.84
     studios
    0.83
     tables
    0.82
     rooms
    0.80
     kitchens
    0.76
     OFFICES
    0.75
    Tables
    0.75
     apartments
    0.75
    Activations Density 4.180%

    No Known Activations