© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6367
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to seeking or giving help, particularly in the context of technical problems or relationship advice.

    oai_token-act-pair · gemini-2.0-flash

    Exclamations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Мексичка
    -0.69
     dataSnapshot
    -0.65
    abestanden
    -0.62
     beginnetje
    -0.60
    ExecuteReader
    -0.57
     стоковая
    -0.56
    aronder
    -0.56
    ebenarnya
    -0.56
    Портали
    -0.56
    쳇
    -0.54
    POSITIVE LOGITS
    ^^
    0.60
    !!
    0.60
    !!!
    0.57
    !!!!
    0.54
     !!
    0.53
    !
    0.53
    ItemBackground
    0.53
    ..
    0.52
    !!!!!
    0.50
     !!!
    0.50
    Activations Density 1.802%

    No Known Activations