© 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. 12520
    Prev
    Next
    INDEX
    Explanations

    descriptions of wind, breezes, and air, especially in relation to caves or the sea

    oai_token-act-pair · gemini-2.0-flash

    vocabulary related to wind

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

    wind

    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
    setVerticalGroup
    -0.74
     protoimpl
    -0.73
     Wikimedijinoj
    -0.64
     ProtoMessage
    -0.63
    prüche
    -0.63
     cdti
    -0.63
    MigrationBuilder
    -0.63
     myſelf
    -0.63
     Audiodateien
    -0.60
     smtplib
    -0.60
    POSITIVE LOGITS
     wind
    1.88
     winds
    1.66
    wind
    1.64
     Wind
    1.52
    Wind
    1.45
     WIND
    1.42
     blowing
    1.36
    WIND
    1.35
    winds
    1.34
     Winds
    1.28
    Activations Density 1.851%

    No Known Activations