© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14138
    Prev
    Next
    INDEX
    Explanations

    the word 'of' or past-tense action verbs.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    bootstrapcdn
    -0.58
     sobą
    -0.51
     GenerationType
    -0.50
    kadang
    -0.48
    ///</
    -0.47
     MainAxisSize
    -0.47
    XmlAccessorType
    -0.44
    每一个
    -0.44
    Traveler
    -0.44
     muchos
    -0.44
    POSITIVE LOGITS
     sever
    0.69
    数
    0.68
     literally
    0.66
     quite
    0.64
    quite
    0.63
     scores
    0.63
     Diver
    0.61
     roughly
    0.60
    SEVER
    0.60
     hardly
    0.59
    Activations Density 1.909%

    No Known Activations