© 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. 8509
    Prev
    Next
    INDEX
    Explanations

    the word "practices" or the word "practice"

    oai_token-act-pair · gemini-2.0-flash

    practice

    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
    <eos>
    -0.65
     officielles
    -0.53
     ferons
    -0.52
     religieuses
    -0.52
     praktis
    -0.52
     extérieurs
    -0.51
     rire
    -0.50
     venons
    -0.50
     prestazioni
    -0.50
     nationaux
    -0.50
    POSITIVE LOGITS
     itſelf
    0.89
    adpleegd
    0.87
    lihood
    0.78
     Houſe
    0.78
     Anſ
    0.78
     myſelf
    0.73
     Perſ
    0.72
     Reſ
    0.69
    tude
    0.68
    IVEREF
    0.68
    Activations Density 0.221%

    No Known Activations