© 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. 6883
    Prev
    Next
    INDEX
    Explanations

    the words "give" in the context of asking someone to contact you or with an object following "give"

    oai_token-act-pair · gemini-2.0-flash

    articles and determiners

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

    articles

    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
    клопе
    -0.66
     AttributeSet
    -0.63
    iprot
    -0.61
    parseFrom
    -0.60
     arşivlendi
    -0.60
    migrationBuilder
    -0.58
    Personendaten
    -0.57
     autorytatywna
    -0.56
    EDEFAULT
    -0.56
    ThroughAttribute
    -0.55
    POSITIVE LOGITS
     a
    1.89
     một
    0.89
     einen
    0.88
     einem
    0.86
     eine
    0.80
     یک
    0.80
     एक
    0.79
    einem
    0.79
     an
    0.78
     einer
    0.74
    Activations Density 1.672%

    No Known Activations