© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2511
    Prev
    Next
    INDEX
    Explanations

    function words, especially pronouns and articles

    oai_token-act-pair · gemini-2.0-flash

    say "nouns"

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Work
    -1.14
     genoux
    -1.07
     cérami
    -1.07
     Hand
    -1.06
     For
    -1.06
     Use
    -1.05
     fermés
    -1.05
     Out
    -1.05
     Set
    -1.05
     boî
    -1.05
    POSITIVE LOGITS
     Portuguesa
    0.30
     Ślą
    0.27
     sensations
    0.26
     fallacy
    0.26
     intuitively
    0.25
     ramifications
    0.25
     psychotic
    0.24
     restrained
    0.24
     endowed
    0.24
     abstracted
    0.23
    Activations Density 47.183%

    No Known Activations