© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and some related verbs/articles

    oai_token-act-pair · gemini-2.0-flash

    terms related to user interface methods or programming concepts

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

    I

    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
     étoit
    -0.66
     avoient
    -0.63
     étoient
    -0.63
    تقاوى
    -0.62
    ")==
    -0.58
    RenderAtEndOf
    -0.57
     auroit
    -0.57
     heureuse
    -0.55
     Wikimédia
    -0.54
     يتيمه
    -0.53
    POSITIVE LOGITS
     viewDidLoad
    0.60
     bet
    0.59
    rungsseite
    0.59
     introduced
    0.57
    Hauptartikel
    0.56
    IsContent
    0.55
     sper
    0.52
     text
    0.50
     introduce
    0.49
     dij
    0.49
    Activations Density 0.420%

    No Known Activations