© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4852
    Prev
    Next
    INDEX
    Explanations

    the letters "gu" together

    oai_token-act-pair · gemini-2.0-flash

    gu

    np_max-act · 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
    <bos>
    -1.00
     lack
    -0.71
     host
    -0.71
     ber
    -0.71
     sever
    -0.69
    ātu
    -0.69
    Respons
    -0.68
     Verge
    -0.67
    leger
    -0.66
     presence
    -0.65
    POSITIVE LOGITS
     zijne
    0.88
     mattino
    0.79
     pitié
    0.78
     mourut
    0.77
     mijne
    0.76
     présidenti
    0.75
    ixante
    0.75
    føl
    0.75
     zelve
    0.74
     autorité
    0.74
    Activations Density 2.161%

    No Known Activations