© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, political issues, and programming code

    oai_token-act-pair · gemini-2.0-flash

    unknownFields

    np_max-act · gemini-2.0-flash

    unknownFields

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Theſe
    -0.85
    Удачи
    -0.83
     Arxivat
    -0.82
     myſelf
    -0.82
     Hogarth
    -0.79
     Nacionales
    -0.79
     posibil
    -0.78
     RSSSF
    -0.78
     himſelf
    -0.75
     whoſe
    -0.75
    POSITIVE LOGITS
    
    0.94
    
    0.92
     BrowserModule
    0.79
    ьаж
    0.79
    /*
    0.78
     ActiveRecord
    0.77
     متعلقه
    0.77
     esternos
    0.73
    providedIn
    0.72
     שוליים
    0.72
    Activations Density 11.537%

    No Known Activations