© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gemini-2.0-flash

    as

    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
     électroniques
    -0.61
     sauvages
    -0.58
     automatiques
    -0.58
     industriels
    -0.54
     européennes
    -0.52
     juger
    -0.52
     nationaux
    -0.49
     leçons
    -0.49
     religieuses
    -0.48
     scolaires
    -0.48
    POSITIVE LOGITS
     ་་
    0.38
     zirc
    0.37
     RSP
    0.37
     GUR
    0.37
     Realt
    0.37
     RIT
    0.36
     Ballon
    0.35
     IFT
    0.35
     NIN
    0.35
     Wot
    0.34
    Activations Density 48.258%

    No Known Activations