© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13926
    Prev
    Next
    INDEX
    Explanations

    text followed by words like 'you', 'your', 'recommend', 'like', 'cases', 'but' and 'tests'

    oai_token-act-pair · gemini-2.0-flash

    personal interactions

    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
     your
    -2.44
    your
    -2.25
    Your
    -2.14
     Your
    -2.00
    YOUR
    -1.86
    你的
    -1.66
     YOUR
    -1.62
    Ваш
    -1.60
    您的
    -1.55
     Votre
    -1.48
    POSITIVE LOGITS
    だが
    0.79
    であるが
    0.69
    だったが
    0.67
     my
    0.56
    ものである
    0.55
    のである
    0.53
    جمعیت
    0.52
    のだが
    0.51
    である
    0.48
     her
    0.47
    Activations Density 3.061%

    No Known Activations