© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15138
    Prev
    Next
    INDEX
    Explanations

    math equations, especially those involving derivatives

    oai_token-act-pair · gemini-2.0-flash

    find solve

    np_max-act · gemini-2.0-flash

    math prompts

    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
     utafitiHapana
    -1.13
     ſmall
    -0.93
    ^(@)
    -0.90
    ]='\
    -0.88
     cauſe
    -0.83
    BibitemShut
    -0.82
    >\<^
    -0.82
     greateſt
    -0.81
     itſelf
    -0.81
     متعلقه
    -0.79
    POSITIVE LOGITS
    <bos>
    1.76
    ↵↵
    1.05
    '
    0.94
    ↵
    0.71
    .
    0.70
    ’
    0.67
     
    0.59
    \
    0.52
    ↵↵↵
    0.52
    A
    0.52
    Activations Density 7.213%

    No Known Activations