© 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. 4897
    Prev
    Next
    INDEX
    Explanations

    different variations of the word "there"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "There"

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

    There

    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
    WebServlet
    -0.72
    ParallelGroup
    -0.61
    routeProvider
    -0.57
    bootstrapcdn
    -0.57
    TagHelper
    -0.57
     Assertion
    -0.50
    incoming
    -0.50
     Courant
    -0.49
    Välislingid
    -0.49
    ulsory
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.67
     CreateTagHelper
    0.66
     Roskov
    0.58
    chenkt
    0.56
     UIFont
    0.55
    StructEnd
    0.53
     للاسماء
    0.51
    ISupport
    0.51
    жели
    0.50
     HttpHeaders
    0.49
    Activations Density 0.414%

    No Known Activations