© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7123
    Prev
    Next
    INDEX
    Explanations

    the word "per" near numbers or units of measurement

    oai_token-act-pair · gemini-2.0-flash

    time-related terms

    np_token-act-pair-logits · gpt-4o-mini

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.97
    CloseOperation
    -0.86
    OGND
    -0.83
     typelib
    -0.82
    sidemargin
    -0.79
    addCriterion
    -0.79
     CreateTagHelper
    -0.77
    ///</
    -0.77
     esternos
    -0.73
     EdgeInsets
    -0.71
    POSITIVE LOGITS
     month
    0.77
     hour
    0.72
     year
    0.72
     week
    0.66
     day
    0.65
     minute
    0.55
     can
    0.52
     work
    0.51
     cup
    0.49
     uur
    0.49
    Activations Density 1.826%

    No Known Activations