© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5501
    Prev
    Next
    INDEX
    Explanations

    hotel advertising

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Lodging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Sharing
    -0.62
     Singles
    -0.62
     sharing
    -0.62
    shared
    -0.61
     shared
    -0.60
     singles
    -0.58
     private
    -0.57
     Sharing
    -0.57
    Shared
    -0.57
    日閲覧
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.57
    odha
    0.50
     turn
    0.50
    djangoproject
    0.49
    jago
    0.49
     CreateTagHelper
    0.47
     Turn
    0.47
     mourir
    0.45
     morire
    0.44
    <tfoot>
    0.44
    Activations Density 0.245%

    No Known Activations