© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10302
    Prev
    Next
    INDEX
    Explanations

    words related to weather, sunlight, and nature

    oai_token-act-pair · gemini-2.0-flash

    sun

    np_max-act · gemini-2.0-flash

    sunlight

    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
    SourceChecksum
    -0.77
    ngdoc
    -0.64
     GetEnumerator
    -0.62
     EconPapers
    -0.61
    mergeFrom
    -0.58
    offsetof
    -0.57
    DockStyle
    -0.55
     szóci
    -0.55
    verwijspagina
    -0.54
    PositiveButton
    -0.54
    POSITIVE LOGITS
     sun
    0.64
     typelib
    0.63
    orianCalendar
    0.60
     sunlight
    0.60
     rain
    0.59
    mybatisplus
    0.59
     snowfall
    0.57
     snows
    0.57
     darkness
    0.56
     digitais
    0.56
    Activations Density 1.019%

    No Known Activations