© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6332
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

    oai_token-act-pair · gemini-2.0-flash

    chert

    np_max-act · gemini-2.0-flash

    say "▁"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Rüyada
    -0.76
    ↵↵
    -0.74
    
    -0.72
    횟
    -0.66
     either
    -0.65
     the
    -0.62
     ambientales
    -0.59
    mstyle
    -0.57
    tvguidetime
    -0.57
    getchar
    -0.57
    POSITIVE LOGITS
     rhestr
    0.69
    ipheral
    0.66
    ésult
    0.63
    esterday
    0.63
    ficulty
    0.63
     Efq
    0.62
     möjligt
    0.61
     ſhe
    0.60
    drawal
    0.60
     becauſe
    0.60
    Activations Density 12.463%

    No Known Activations