© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14953
    Prev
    Next
    INDEX
    Explanations

    mentions of Russia in connection to international attacks and military terms

    oai_token-act-pair · gemini-2.0-flash

    Russia, Soviet Union, war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Réponses
    -0.92
    UrlResolution
    -0.71
    DockStyle
    -0.67
    adaptiveStyles
    -0.59
    httphttps
    -0.59
    Tembelea
    -0.59
    RefNanny
    -0.57
    DoubleQuotes
    -0.55
     صوتيه
    -0.55
     Wicidata
    -0.54
    POSITIVE LOGITS
     dataSnapshot
    0.47
     Waite
    0.46
    unhofer
    0.44
    ValueStyle
    0.43
    cort
    0.43
     dAtA
    0.42
    Может
    0.41
    Nazionale
    0.41
    DataSnapshot
    0.40
    Atsauces
    0.39
    Activations Density 1.453%

    No Known Activations