© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    words related to seasons, especially winter, fall, and spring

    oai_token-act-pair · gemini-2.0-flash

    winter

    np_max-act · gemini-2.0-flash

    winter

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     winter
    -1.68
    winter
    -1.66
    Winter
    -1.63
     Winter
    -1.55
     WINTER
    -1.53
    WINTER
    -1.45
     invierno
    -1.16
     winters
    -1.06
     vinter
    -1.03
    summer
    -0.95
    POSITIVE LOGITS
    تاريخ
    0.52
    endforeach
    0.49
    ي
    0.49
     official
    0.49
    urtstag
    0.49
    天
    0.48
    pahan
    0.48
    picasso
    0.47
    IFER
    0.47
    mability
    0.47
    Activations Density 0.524%

    No Known Activations