© 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. 7189
    Prev
    Next
    INDEX
    Explanations

    French words/phrases that might be found in opera lyrics

    oai_token-act-pair · gemini-2.0-flash

    sounds

    np_max-act-logits · gemini-2.0-flash

    French

    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
     Exacts
    -0.60
    ControllerAdvice
    -0.56
     AssemblyCulture
    -0.56
    ftagPool
    -0.54
    RuleContext
    -0.54
    bootstrapcdn
    -0.54
     Référence
    -0.52
    Tembelea
    -0.51
     Eskimo
    -0.51
    ništvo
    -0.50
    POSITIVE LOGITS
    Clik
    0.56
    Sound
    0.56
     đơn
    0.55
    zene
    0.50
     Sound
    0.50
     sounds
    0.49
     SOUND
    0.49
    chst
    0.48
     Pál
    0.48
     sound
    0.47
    Activations Density 0.695%

    No Known Activations