© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11872
    Prev
    Next
    INDEX
    Explanations

    mentions of professional mental health services and practitioners

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to therapy and treatment

    np_token-act-pair-logits · gpt-4o-mini

    Diverse texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     tasse
    -0.53
     Schumann
    -0.50
    setVerticalGroup
    -0.48
     urod
    -0.47
    /**
    -0.47
     reliability
    -0.46
     Fascism
    -0.46
    NameInMap
    -0.45
    riwal
    -0.45
     Third
    -0.45
    POSITIVE LOGITS
     وتسجيلات
    0.68
     >=",
    0.68
    NamedQueries
    0.62
     mergeFrom
    0.60
    Abitanti
    0.59
     تضيفلها
    0.56
    LLocation
    0.52
    getMinutes
    0.52
    Rhestr
    0.52
     Мексичка
    0.49
    Activations Density 1.646%

    No Known Activations