© 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. 5197
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "a" after certain common words

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash

    descriptors indicating size or magnitude

    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
     AspNetCore
    -0.67
     EconPapers
    -0.65
    LookAnd
    -0.64
     intStringLen
    -0.63
    idhi
    -0.63
    CloseOperation
    -0.63
    كذا
    -0.62
     חיצוניים
    -0.61
     CreateTagHelper
    -0.60
    odeon
    -0.59
    POSITIVE LOGITS
     big
    0.58
    PreferredItem
    0.53
     tricky
    0.51
    
    0.51
     []:
    0.51
     BIG
    0.50
     pretty
    0.50
     tall
    0.47
    big
    0.47
     dangerous
    0.46
    Activations Density 1.302%

    No Known Activations