© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4228
    Prev
    Next
    INDEX
    Explanations

    words that are used in an academic or formal context to describe how to get the best possible outcome

    oai_token-act-pair · gemini-2.0-flash

    Best

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    xfb
    -0.51
     transférez
    -0.47
    Carreira
    -0.45
    しら
    -0.44
    Bibliograf
    -0.44
    ANTLR
    -0.42
    parsedMessage
    -0.41
     Können
    -0.40
     Genti
    -0.40
    GeneratedMessage
    -0.40
    POSITIVE LOGITS
     best
    1.99
    best
    1.79
    Best
    1.51
     optimal
    1.44
     terbaik
    1.42
    BEST
    1.42
     Best
    1.39
    最佳
    1.38
     BEST
    1.38
     optimum
    1.36
    Activations Density 2.008%

    No Known Activations