© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11085
    Prev
    Next
    INDEX
    Explanations

    the word "mutual" and words nearby, sometimes with activation if the nearby word is a noun

    oai_token-act-pair · gemini-2.0-flash

    mutual

    np_max-act · gemini-2.0-flash
    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
    tvguidetime
    -1.47
     photolibrary
    -1.34
    berdayakan
    -1.27
     itſelf
    -1.26
     $_"
    -1.25
     Majefty
    -1.24
     CURIAM
    -1.22
    .」
    -1.22
    .")
    -1.20
     Houſe
    -1.20
    POSITIVE LOGITS
     
    0.88
      
    0.63
    :
    0.56
    >
    0.55
    <
    0.54
    <strong>
    0.54
    2
    0.54
     che
    0.54
     (
    0.53
     in
    0.52
    Activations Density 2.800%

    No Known Activations