© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7196
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to recurring events with possible commercial aspect

    oai_token-act-pair · gemini-2.0-flash

    Events and gatherings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ſelf
    -0.91
    出版年
    -0.86
     purpoſe
    -0.84
     iſt
    -0.78
     contextLoads
    -0.77
    جوايز
    -0.77
     ſtate
    -0.77
    ſelves
    -0.75
     ſche
    -0.75
     Monfieur
    -0.75
    POSITIVE LOGITS
     To
    0.47
     bash
    0.47
    bash
    0.46
     Bash
    0.46
    urlencoded
    0.46
     der
    0.45
     Ext
    0.44
     faire
    0.43
    kú
    0.43
    Bash
    0.43
    Activations Density 3.236%

    No Known Activations