© 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. 5102
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical values related to experimental measurements, especially in scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    tokens mixed with non-English elements

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

    Time periods in hours

    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
    richTextPanel
    -1.04
     мәкал
    -0.91
    BeginContext
    -0.90
     Signalez
    -0.86
    SharedCtor
    -0.85
     صوتيه
    -0.85
     <=",
    -0.85
    ParallelGroup
    -0.83
     يتيمه
    -0.79
    Билгалдахарш
    -0.79
    POSITIVE LOGITS
    hin
    0.43
    场
    0.38
    ссора
    0.38
     seventy
    0.37
    setzungen
    0.36
     Du
    0.36
    eiro
    0.35
     du
    0.35
     cu
    0.34
    খ
    0.33
    Activations Density 2.348%

    No Known Activations