© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2350
    Prev
    Next
    INDEX
    Explanations

    words or notations related to measurement, calculation, or experimentation in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    division

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    новниш
    -0.72
    AddTagHelper
    -0.71
    例句
    -0.69
    AndEndTag
    -0.68
    __':
    -0.68
    تقاوى
    -0.65
    :✨
    -0.65
    sidemargin
    -0.63
    Демографія
    -0.62
    évaluateur
    -0.60
    POSITIVE LOGITS
     divided
    1.75
     divide
    1.60
     dividing
    1.53
     divides
    1.42
     Divided
    1.41
    divided
    1.39
     Divide
    1.31
     divid
    1.30
     division
    1.29
     divis
    1.29
    Activations Density 5.767%

    No Known Activations