© 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. 492
    Prev
    Next
    INDEX
    Explanations

    mostly danish words, possibly related to titles or names

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    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
     Kaly
    -0.59
     betweenstory
    -0.57
     is
    -0.56
    bootstrapcdn
    -0.55
    DrawerToggle
    -0.54
    COUVER
    -0.54
     Kors
    -0.53
    ruptedException
    -0.52
    getSystemService
    -0.51
    signable
    -0.50
    POSITIVE LOGITS
     initComponents
    0.65
     bruges
    0.64
     brukes
    0.63
     findes
    0.59
    TestingModule
    0.54
     finnes
    0.54
     tycker
    0.53
     fungerar
    0.52
     fortæller
    0.52
     används
    0.51
    Activations Density 0.255%

    No Known Activations