© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15676
    Prev
    Next
    INDEX
    Explanations

    legal citations with a 1-, 2-, 4-, or 5-digit number

    oai_token-act-pair · gemini-2.0-flash

    say "zero"

    np_max-act-logits · gemini-2.0-flash
    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
     Efq
    -1.00
     itſelf
    -0.96
     BoxFit
    -0.96
     myſelf
    -0.93
     ―――――
    -0.90
    ^(@)
    -0.87
     Вікі
    -0.86
    Попис
    -0.84
     Мексичка
    -0.84
     Forumite
    -0.84
    POSITIVE LOGITS
     zero
    1.38
     Zero
    1.16
    zero
    1.14
    Zero
    1.09
     cero
    1.01
     zéro
    0.95
    ZERO
    0.91
     ZERO
    0.91
    零
    0.84
    0
    0.82
    Activations Density 0.508%

    No Known Activations