© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12397
    Prev
    Next
    INDEX
    Explanations

    specific values with certain units like degrees Celsius, minutes, and seconds

    oai_token-act-pair · gemini-2.0-flash

    references to time duration in minutes

    np_token-act-pair-logits · gpt-4o-mini

    Minutes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    oredCriteria
    -0.68
     AssemblyCompany
    -0.58
     protoimpl
    -0.57
    tenth
    -0.55
     casque
    -0.55
     tenth
    -0.55
    tsen
    -0.53
     समीक्षक
    -0.53
    ertia
    -0.52
    ItemBackground
    -0.52
    POSITIVE LOGITS
     minute
    1.45
     minutes
    1.25
    minute
    1.23
     Minute
    1.13
    Minute
    1.12
     MINUTE
    1.05
     Minutes
    1.02
    min
    1.02
    minutes
    0.99
     min
    0.97
    Activations Density 2.460%

    No Known Activations