© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11487
    Prev
    Next
    INDEX
    Explanations

    strings that are parts of URLs, paths, or code

    oai_token-act-pair · gemini-2.0-flash

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    *
    -0.46
    subpackage
    -0.43
     CEO
    -0.42
    決
    -0.41
    "
    -0.39
    :
    -0.38
    ين
    -0.38
     rarely
    -0.37
    人和
    -0.37
    klassi
    -0.36
    POSITIVE LOGITS
     Roskov
    1.01
    ValueStyle
    0.94
    קישורים
    0.92
    rungsseite
    0.90
    parsedMessage
    0.88
     kaarangay
    0.87
    rrggbb
    0.86
    ">//
    0.85
     متعلقه
    0.82
    
    0.82
    Activations Density 1.299%

    No Known Activations