© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9272
    Prev
    Next
    INDEX
    Explanations

    words that appear in academic research papers

    oai_token-act-pair · gemini-2.0-flash

    Scientific/academic texts

    np_max-act-logits · gemini-2.0-flash

    base-form verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Are
    -0.70
     Are
    -0.69
     Were
    -0.63
    Were
    -0.61
     voltak
    -0.51
    were
    -0.50
    ARE
    -0.50
    Šaltiniai
    -0.49
     ARE
    -0.48
     meubles
    -0.47
    POSITIVE LOGITS
     require
    1.28
     happen
    1.20
     remain
    1.20
     include
    1.15
     provide
    1.15
     occur
    1.13
     describe
    1.13
     continue
    1.13
     rely
    1.12
     consume
    1.12
    Activations Density 23.018%

    No Known Activations