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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4956
    Prev
    Next
    INDEX
    Explanations

    capitalized words and phrases, often related to titles, locations, or organizations

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash

    Night Method used: 1 — because MAX_ACTIVATING_TOKENS are time/occasion words, predominantly "Night"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Trip
    -0.69
     Walkover
    -0.65
    internalType
    -0.61
     Shift
    -0.61
    Trip
    -0.61
    ("}");
    -0.60
     Sequel
    -0.60
    шеб
    -0.59
     Turnier
    -0.59
     Rain
    -0.59
    POSITIVE LOGITS
     day
    0.69
     week
    0.68
     early
    0.66
     eventful
    0.65
     trek
    0.65
     time
    0.62
     episode
    0.62
     days
    0.61
    Πηγή
    0.61
    numerusform
    0.61
    Activations Density 5.153%

    No Known Activations