© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15131
    Prev
    Next
    INDEX
    Explanations

    words and names of people, locations, and organizations involved in legal cases

    oai_token-act-pair · gemini-2.0-flash

    Foreign words for "similar"

    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
     park
    -0.59
     sport
    -0.58
     travel
    -0.57
     green
    -0.57
     road
    -0.55
     fire
    -0.55
     garden
    -0.54
     golf
    -0.53
     sports
    -0.53
     air
    -0.52
    POSITIVE LOGITS
     varandra
    0.78
     liknande
    0.75
     mismos
    0.75
     medesimo
    0.75
     senare
    0.73
     ytterligare
    0.71
     senere
    0.69
     myö
    0.69
     eenig
    0.69
     stessa
    0.68
    Activations Density 5.855%

    No Known Activations