© 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. 12402
    Prev
    Next
    INDEX
    Explanations

    apostrophes, likely indicating possessives or contractions

    oai_token-act-pair · gemini-2.0-flash

    the character "'"

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

    apostrophe

    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
    клопе
    -0.57
     FetchType
    -0.57
    extAlignment
    -0.52
    EndProject
    -0.50
     Roskov
    -0.48
     numberOfRows
    -0.47
    bleau
    -0.46
    Géographie
    -0.46
     stihl
    -0.44
     dAtA
    -0.44
    POSITIVE LOGITS
    use
    0.66
    enumi
    0.65
     makeStyles
    0.65
    ⓘ
    0.63
     surla
    0.63
    IUrlHelper
    0.60
    ArgsConstructor
    0.55
     használat
    0.54
    
    0.54
     use
    0.53
    Activations Density 0.258%

    No Known Activations