© 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. 3779
    Prev
    Next
    INDEX
    Explanations

    marketing sales language

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    expandindo
    -0.63
     Wikimedijinoj
    -0.53
     mergeFrom
    -0.51
    \}\\
    -0.49
    __.__
    -0.48
    }>;
    -0.48
     متعلقه
    -0.46
     recalled
    -0.46
     post
    -0.46
     resa
    -0.46
    POSITIVE LOGITS
     Contact
    0.70
     contact
    0.68
     contactez
    0.68
    Contact
    0.66
     Monfieur
    0.64
     contacter
    0.63
    SpringBootTest
    0.63
    contact
    0.63
     whoſe
    0.63
     Jefus
    0.62
    Activations Density 1.245%

    No Known Activations