© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    clauses describing quantities or measurements

    oai_token-act-pair · gemini-2.0-flash

    trips and journeys

    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
     tour
    -1.13
     trip
    -1.06
     run
    -0.94
     Tour
    -0.92
     visit
    -0.91
     walk
    -0.89
     ride
    -0.87
    tour
    -0.86
    Tour
    -0.85
    trip
    -0.82
    POSITIVE LOGITS
     st
    0.66
     تانيه
    0.62
     tre
    0.62
    astéroïdes
    0.61
    :✨
    0.57
     OkHttpClient
    0.54
     comm
    0.53
    ніципа
    0.52
    省市镇
    0.52
    ROIT
    0.51
    Activations Density 6.799%

    No Known Activations