© 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. 5099
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with studies involving people, particularly children or patients, and their behaviors or conditions

    oai_token-act-pair · gemini-2.0-flash

    words indicating repetition or plurality

    np_token-act-pair-logits · gpt-4o-mini
    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
    شهاد
    -0.75
    ingtones
    -0.73
     otomatig
    -0.68
    ]")]
    -0.64
    atering
    -0.64
    migrationBuilder
    -0.63
     فريبيس
    -0.60
     الحره
    -0.60
    Hentet
    -0.60
    ^(@)
    -0.57
    POSITIVE LOGITS
     each
    0.63
     <<<<<<<<<<<<<<
    0.57
    each
    0.56
     Each
    0.55
    Each
    0.54
     —
    0.47
    multiple
    0.46
     who
    0.43
    right
    0.43
    Multiple
    0.43
    Activations Density 13.213%

    No Known Activations