Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14427
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with gatherings of people

    oai_token-act-pair · gemini-2.0-flash

    people gathering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rungsseite
    -1.02
     تانيه
    -0.87
    URLException
    -0.86
    ValueStyle
    -0.80
    TagHelper
    -0.77
     AssemblyCulture
    -0.76
     kasarigan
    -0.74
    Geplaatst
    -0.74
    bootstrapcdn
    -0.73
    migrationBuilder
    -0.72
    POSITIVE LOGITS
    trick
    0.65
     filtered
    0.62
     file
    0.60
     trick
    0.59
     stream
    0.59
     trickle
    0.58
     flock
    0.56
     filters
    0.56
    Trick
    0.56
     filtering
    0.55
    Activations Density 2.022%

    No Known Activations