© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3972
    Prev
    Next
    INDEX
    Explanations

    reported speech, especially seeking comment regarding legal and bureaucratic issues

    oai_token-act-pair · gemini-2.0-flash

    Contacting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     beginnetje
    -0.67
    UnusedPrivate
    -0.65
     Мексичка
    -0.64
    SequentialGroup
    -0.62
    InjectAttribute
    -0.60
    yntaxException
    -0.59
     Anſ
    -0.58
    IANGLES
    -0.58
    uxxxx
    -0.56
    Биография
    -0.56
    POSITIVE LOGITS
     contacting
    1.07
     contacted
    0.93
     contact
    0.90
     attempts
    0.90
     attempted
    0.88
     Attempts
    0.83
     Contact
    0.83
    Contact
    0.79
    Attempts
    0.78
     calls
    0.78
    Activations Density 1.466%

    No Known Activations