© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1798
    Prev
    Next
    INDEX
    Explanations

    legal language related to evidence and court rulings, and also the phrase "we can also"

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    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
     mention
    -1.48
     Mention
    -1.43
     mentions
    -1.40
    Mention
    -1.36
    mention
    -1.26
     mentioning
    -1.22
     Mentions
    -1.11
     cite
    -1.10
     mentioned
    -1.09
     cited
    -1.09
    POSITIVE LOGITS
    Personensuche
    0.59
     NSCoder
    0.56
     BorderRadius
    0.55
     متحده
    0.55
    зулта
    0.50
    Fordítás
    0.49
     AssemblyCompany
    0.49
    StreetMap
    0.48
     Benth
    0.48
    transQ
    0.48
    Activations Density 3.655%

    No Known Activations