© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    the word "is" used in questions, often in technical contexts

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "Is"

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

    Is

    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
     me
    -0.48
     mnie
    -0.40
     будете
    -0.40
     мной
    -0.40
     lesquels
    -0.40
     lesquelles
    -0.39
    Me
    -0.39
     Pued
    -0.37
    僕は
    -0.37
     tandis
    -0.36
    POSITIVE LOGITS
     it
    1.09
    findpost
    1.06
     }}"></
    0.89
    
    0.87
    uxxxx
    0.85
    StoryboardSegue
    0.82
    oredCriteria
    0.81
    setVerticalGroup
    0.80
    KommentareTeilen
    0.80
     initComponents
    0.80
    Activations Density 6.644%

    No Known Activations