© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15181
    Prev
    Next
    INDEX
    Explanations

    words related to agriculture, particularly rice and sugar plantations

    oai_token-act-pair · gemini-2.0-flash

    agricultural products

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    insertBefore
    -0.41
     bekym
    -0.41
     Hesper
    -0.40
     vistos
    -0.39
    不着
    -0.39
    balik
    -0.39
    igsaw
    -0.38
    osit
    -0.38
     Meinung
    -0.38
     matrimonial
    -0.37
    POSITIVE LOGITS
    setVerticalGroup
    0.90
    جغرافيا
    0.83
     BoxFit
    0.81
     autorytatywna
    0.77
    SequentialGroup
    0.75
    Parcelize
    0.74
    XmlAccessType
    0.68
     Audiodateien
    0.67
     CreateTagHelper
    0.63
     <<<<<<<<<<<<<<
    0.63
    Activations Density 1.519%

    No Known Activations