© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5167
    Prev
    Next
    INDEX
    Explanations

    Russian language text mixed with code-related terms

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
    InvalidProtocol
    -0.88
    Personendaten
    -0.86
     nahilalakip
    -0.86
     تضيفلها
    -0.84
     Monfieur
    -0.82
     Majefty
    -0.79
     houſe
    -0.78
     Houſe
    -0.78
     ſeveral
    -0.77
     whoſe
    -0.76
    POSITIVE LOGITS
    utscher
    0.41
    esModule
    0.40
     tra
    0.39
    PRNewswire
    0.36
    Essay
    0.36
    HIRE
    0.35
     mi
    0.34
     Te
    0.34
    enservice
    0.34
     k
    0.34
    Activations Density 0.185%

    No Known Activations