© 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. 12455
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by auxiliary verbs, especially those followed by 'to'

    oai_token-act-pair · gemini-2.0-flash

    code-related terminology and expressions

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

    to

    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
    solete
    -0.57
    etak
    -0.50
    बार
    -0.46
     yyr
    -0.45
     ((*
    -0.44
    thâu
    -0.44
    ::{
    -0.44
     half
    -0.43
    iseur
    -0.43
    ueba
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.91
    mybatisplus
    0.78
     CreateTagHelper
    0.76
    ########.
    0.71
    новништво
    0.69
    BeginContext
    0.67
     ReactDOM
    0.64
    StructEnd
    0.60
     betweenstory
    0.60
     propOrder
    0.60
    Activations Density 3.314%

    No Known Activations