© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9137
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to late-stage pregnancy and labor

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens

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

    Labor and birth

    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
     delivered
    -0.76
     delivery
    -0.75
    delivered
    -0.73
     deliveries
    -0.72
     Delivery
    -0.67
     Delivered
    -0.66
    Delivery
    -0.66
     DELIVER
    -0.60
    delivery
    -0.58
    Delivered
    -0.58
    POSITIVE LOGITS
     חיצוניים
    0.76
     Roskov
    0.70
    principalTable
    0.68
     مشين
    0.65
    StoreMessageInfo
    0.63
     kaynağından
    0.57
     <=",
    0.57
    SourceChecksum
    0.55
    izoen
    0.52
    Surge
    0.52
    Activations Density 1.374%

    No Known Activations