© 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. 5335
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and statistical analysis

    oai_token-act-pair · gemini-2.0-flash

    Scientific data with numbers

    np_max-act-logits · gemini-2.0-flash

    say "symbols"

    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
     È
    -0.38
     è
    -0.37
    ○
    -0.34
     é
    -0.34
     Donc
    -0.33
     å
    -0.33
    Paradox
    -0.33
    â
    -0.32
    <0xEF>
    -0.32
     à
    -0.32
    POSITIVE LOGITS
     Theſe
    0.66
     مرئيه
    0.63
    MemoryWarning
    0.62
     AspNetCore
    0.62
     Jefus
    0.60
    Fordítás
    0.60
    loài
    0.58
     becauſe
    0.57
     ProtoMessage
    0.57
     EconPapers
    0.56
    Activations Density 9.732%

    No Known Activations