© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13293
    Prev
    Next
    INDEX
    Explanations

    the word "trust," especially in a legal sense

    oai_token-act-pair · gemini-2.0-flash

    trust

    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
    Negative Logits
    1
    -0.97
    2
    -0.91
    4
    -0.85
     
    -0.84
    3
    -0.83
    5
    -0.76
    0
    -0.73
      
    -0.73
    n
    -0.73
    ↵↵
    -0.70
    POSITIVE LOGITS
    numerusform
    1.11
     vectorielle
    1.07
     виправивши
    1.06
    ंदीखरीदारी
    1.05
    rungsseite
    1.05
     tartalomajánló
    1.04
    ]-->
    1.04
    verwijspagina
    1.02
    thâu
    1.01
    Życiorys
    1.00
    Activations Density 2.131%

    No Known Activations