© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5205
    Prev
    Next
    INDEX
    Explanations

    proper nouns or capitalized words

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    np_max-act-logits · gemini-2.0-flash

    say "single letters" Method used: 2 — tokens after max are single letters; say "single letters"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     
    -0.79
    ↵
    -0.75
     (
    -0.74
    ↵↵
    -0.71
     "
    -0.68
     -
    -0.66
    <eos>
    -0.65
     und
    -0.61
     '
    -0.61
     in
    -0.61
    POSITIVE LOGITS
    Personendaten
    1.49
     EconPapers
    1.40
     itſelf
    1.32
     '\\;'
    1.29
     <>",
    1.27
     myſelf
    1.27
     Мексичка
    1.26
     كومونز
    1.26
     typelib
    1.24
     Efq
    1.23
    Activations Density 12.121%

    No Known Activations