© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9645
    Prev
    Next
    INDEX
    Explanations

    text describing the interaction of sunlight and water with surfaces and the land

    oai_token-act-pair · gemini-2.0-flash

    sun and sunlight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    
    -0.77
     CreateTagHelper
    -0.75
    LookAnd
    -0.72
    ollectionView
    -0.67
     Vikipedi
    -0.66
    Obrázky
    -0.65
    protoc
    -0.63
     HomeComponent
    -0.63
     unknownFields
    -0.63
    ValueStyle
    -0.63
    POSITIVE LOGITS
     sunlight
    0.93
     sun
    0.84
    sun
    0.76
     sunshine
    0.76
     light
    0.71
    Sunlight
    0.70
     солне
    0.69
     rain
    0.66
     SUN
    0.65
    Sunshine
    0.65
    Activations Density 1.090%

    No Known Activations