© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14444
    Prev
    Next
    INDEX
    Explanations

    words related to contacting an entity for information or assistance

    oai_token-act-pair · gemini-2.0-flash

    contact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     contact
    -2.81
    contact
    -2.48
     Contact
    -2.45
    Contact
    -2.44
     CONTACT
    -2.23
     contacto
    -2.06
    CONTACT
    -2.03
     contacts
    -1.94
     kontakt
    -1.79
     contacting
    -1.77
    POSITIVE LOGITS
    ographs
    0.59
    igshid
    0.56
    monary
    0.56
    eze
    0.56
    canf
    0.55
     Marque
    0.53
     obes
    0.53
    xions
    0.52
     Salv
    0.52
     thrones
    0.52
    Activations Density 1.962%

    No Known Activations