© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    a variety of different features in the text. I am unable to discern one single behavior

    oai_token-act-pair · gemini-2.0-flash

    specific quantities or measurements

    np_token-act-pair-logits · gpt-4o-mini
    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
     autorytatywna
    -0.74
    enumi
    -0.64
    NTIS
    -0.60
    出版年
    -0.57
     Grayson
    -0.56
     hObject
    -0.56
    zupeł
    -0.55
    Ecotoxicity
    -0.55
     thượng
    -0.54
    SourceChecksum
    -0.52
    POSITIVE LOGITS
     ProtoMessage
    0.49
     undercover
    0.49
    êque
    0.48
    voltaic
    0.47
    usercontent
    0.46
    ComponentScan
    0.45
    ScopeManager
    0.45
    BorderFactory
    0.45
    backer
    0.44
    TokenNameRPAREN
    0.44
    Activations Density 0.112%

    No Known Activations