© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13839
    Prev
    Next
    INDEX
    Explanations

    scientific text, including mathematical equations, chemical formulas, and references to experiments

    oai_token-act-pair · gemini-2.0-flash

    Scientific notation/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ReusableCell
    -0.52
    minist
    -0.39
     Charge
    -0.38
    ocellular
    -0.38
    tent
    -0.37
     Tent
    -0.37
     cro
    -0.36
     Ent
    -0.36
    tage
    -0.36
     numerus
    -0.36
    POSITIVE LOGITS
    <bos>
    1.73
     itſelf
    0.89
     myſelf
    0.77
     raiſ
    0.77
    ſelf
    0.73
    Geplaatst
    0.72
     pleaſure
    0.69
     Efq
    0.69
     Monfieur
    0.68
     themſelves
    0.66
    Activations Density 13.885%

    No Known Activations