© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13683
    Prev
    Next
    INDEX
    Explanations

    technical writing and language related to equations, data collection, and systems.

    oai_token-act-pair · gemini-2.0-flash

    obtained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     acquired
    -1.13
     obtained
    -1.05
     gained
    -1.02
     collected
    -0.97
    acquired
    -0.93
     delivered
    -0.90
     Obtained
    -0.90
     received
    -0.88
     encountered
    -0.88
     gathered
    -0.87
    POSITIVE LOGITS
    تقاوى
    0.71
    ICATED
    0.68
     houſe
    0.66
     uſe
    0.65
     Jefus
    0.65
     Chriftian
    0.60
     conva
    0.60
     ſeveral
    0.60
     neceff
    0.60
    })));
    0.59
    Activations Density 5.574%

    No Known Activations