© 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. 5452
    Prev
    Next
    INDEX
    Explanations

    small, common words generally used as prepositions

    oai_token-act-pair · gemini-2.0-flash

    contextual or non-English terms

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

    Text narratives/anime

    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
     pinulongan
    -0.46
    atu
    -0.44
    MLLoader
    -0.42
     höchst
    -0.42
    Abitanti
    -0.42
    ằm
    -0.42
    umo
    -0.41
    stonia
    -0.41
     quitt
    -0.40
    SizeF
    -0.39
    POSITIVE LOGITS
    SequentialGroup
    0.81
    الإنجليزية
    0.79
     betweenstory
    0.74
    BeginContext
    0.70
    Atsauces
    0.65
     Alcott
    0.61
     iprot
    0.60
    makeConstraints
    0.59
    会長
    0.59
     发表于
    0.58
    Activations Density 1.252%

    No Known Activations