© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4777
    Prev
    Next
    INDEX
    Explanations

    the word "neighbors", and sometimes "time", "man", "times", "businesses", "defense" or "paths"

    oai_token-act-pair · gemini-2.0-flash

    neighbors

    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
    ^(@)
    -1.63
    ſelves
    -1.27
     $_"
    -1.25
    ſelf
    -1.24
     doubtnut
    -1.23
     ―――――
    -1.20
    ՚
    -1.18
     ་་
    -1.17
     Efq
    -1.16
    .",
    -1.15
    POSITIVE LOGITS
    ↵
    0.85
      
    0.81
     
    0.77
    1
    0.74
    2
    0.73
     {
    0.71
    0
    0.69
    <unused63>
    0.65
    ↵↵
    0.64
     [
    0.63
    Activations Density 2.394%

    No Known Activations