© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10956
    Prev
    Next
    INDEX
    Explanations

    a variety of legal, financial and other official-sounding words.

    oai_token-act-pair · 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
    ագրություններ
    -0.82
    
    -0.65
    __(/*!
    -0.63
    GMENT
    -0.56
    Datuak
    -0.56
     trị
    -0.55
    `{.
    -0.54
     firefighting
    -0.53
    erapeu
    -0.53
     antim
    -0.53
    POSITIVE LOGITS
    Glej
    0.54
    致
    0.52
     propOrder
    0.52
     énergé
    0.51
     creazione
    0.50
     progettazione
    0.49
     comisiones
    0.48
    IntoConstraints
    0.48
     致
    0.47
     coussin
    0.47
    Activations Density 6.797%

    No Known Activations