© 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. 6719
    Prev
    Next
    INDEX
    Explanations

    words related to amounts or quantities, especially time

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    Time durations

    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
     minute
    -1.66
     minutes
    -1.48
    minute
    -1.45
    Minute
    -1.31
     Minute
    -1.30
     minuto
    -1.27
     MINUTE
    -1.22
    minutes
    -1.21
     Minutes
    -1.20
     minutos
    -1.19
    POSITIVE LOGITS
    oredCriteria
    0.56
    isSet
    0.50
    gione
    0.47
    хьтан
    0.45
    DebuggerStep
    0.45
    ゴリー
    0.44
     ofrecerte
    0.43
    tilled
    0.43
    bille
    0.42
    luğu
    0.42
    Activations Density 2.195%

    No Known Activations