© 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. 4468
    Prev
    Next
    INDEX
    Explanations

    references to the U.S. Forest Service and the U.S. Department of Energy, especially when discussing fire-related incidents

    oai_token-act-pair · gemini-2.0-flash

    US organizations/locations

    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
    DoubleQuotes
    -0.72
    ----</
    -0.56
    mergeFrom
    -0.54
     configureStore
    -0.54
     gynhyrchwyd
    -0.52
    SOUNDBITE
    -0.49
    áček
    -0.49
    unicaciones
    -0.48
    EditorBrowsable
    -0.47
    ProgressHUD
    -0.47
    POSITIVE LOGITS
     US
    0.69
    US
    0.60
    stateMutability
    0.52
    QMetaType
    0.51
     مرئيه
    0.50
     United
    0.50
     financeira
    0.50
    }));
    0.49
     químicas
    0.49
    seamnă
    0.48
    Activations Density 1.555%

    No Known Activations