© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5577
    Prev
    Next
    INDEX
    Explanations

    words pertaining to military conflicts and organizations, particularly those with French or unusual spelling.

    oai_token-act-pair · gemini-2.0-flash

    non-English language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     withal
    -0.64
     overtaken
    -0.59
     ridden
    -0.59
     Pina
    -0.59
     táctil
    -0.58
     Edson
    -0.57
     Aver
    -0.56
     Anu
    -0.56
    nto
    -0.56
     Herd
    -0.56
    POSITIVE LOGITS
    webElementXpaths
    0.64
     Administrativna
    0.56
     चीज़ों
    0.54
     ligiloj
    0.53
    PreferredItem
    0.51
     pinulongan
    0.51
     Wiktionnaire
    0.51
    prüche
    0.50
     Италијани
    0.47
    GEBURTSDATUM
    0.46
    Activations Density 1.246%

    No Known Activations