© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 459
    Prev
    Next
    INDEX
    Explanations

    instances of "you to" and "you" followed by helping verbs

    oai_token-act-pair · gemini-2.0-flash

    Programming and technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tagHelperRunner
    -0.69
     Administrativna
    -0.66
     للمعارف
    -0.64
    Rüyada
    -0.59
     Daß
    -0.59
    richTextPanel
    -0.58
    daß
    -0.57
    archiviato
    -0.57
     kaarangay
    -0.56
    fromnode
    -0.55
    POSITIVE LOGITS
    Geographie
    0.58
    styleable
    0.55
    mergeFrom
    0.54
    CreateMap
    0.53
    iostream
    0.53
    TagHelper
    0.52
     gero
    0.48
    nestjs
    0.48
    UVWXYZ
    0.47
     ExecuteAsync
    0.46
    Activations Density 4.729%

    No Known Activations