© 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. 3826
    Prev
    Next
    INDEX
    Explanations

    words related to official procedures and support

    oai_token-act-pair · gemini-2.0-flash

    officially

    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
     officiellement
    -0.93
     специалисты
    -0.82
     oficialmente
    -0.73
     officielles
    -0.71
     специалистов
    -0.70
     Wissenschaftler
    -0.67
    cepteur
    -0.65
     officielle
    -0.64
    Experts
    -0.63
     Experten
    -0.63
    POSITIVE LOGITS
    prepareStatement
    0.85
     ***/
    0.79
    ſelf
    0.73
     itſelf
    0.71
     ་་
    0.71
    lois
    0.68
     cdti
    0.68
    
    0.68
    >\<^
    0.67
    ⁸
    0.67
    Activations Density 4.104%

    No Known Activations