© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5817
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases, including those relating to community service, food critiques, and locations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ').
    -0.55
     found
    -0.55
    ’).
    -0.54
     поскольку
    -0.52
    }();
    -0.51
     probably
    -0.50
     %).
    -0.50
     actually
    -0.50
     ());
    -0.50
     ré
    -0.50
    POSITIVE LOGITS
     purpoſe
    1.02
     houſe
    1.01
     Jefus
    1.00
     quæ
    0.99
    Rüyada
    0.99
     myſelf
    0.98
     greateſt
    0.97
     Efq
    0.97
     himſelf
    0.96
     Monfieur
    0.96
    Activations Density 11.051%

    No Known Activations