© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8569
    Prev
    Next
    INDEX
    Explanations

    the word "caught" and the Roman numeral "II"

    oai_token-act-pair · gemini-2.0-flash

    caught

    np_max-act · gemini-2.0-flash

    caught

    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
    DockStyle
    -1.12
     Roskov
    -1.11
    SBATCH
    -1.08
     Мексичка
    -1.05
    __":
    -1.03
    ergies
    -0.98
    NewUrlParser
    -0.98
    tonsoft
    -0.96
    voltaic
    -0.96
     AssemblyCulture
    -0.94
    POSITIVE LOGITS
     Diſ
    0.82
     pegat
    0.78
     parís
    0.75
    or
    0.75
    er
    0.75
     houſe
    0.74
    en
    0.72
     Saludos
    0.72
     ſch
    0.71
     Monfieur
    0.71
    Activations Density 2.241%

    No Known Activations