© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2133
    Prev
    Next
    INDEX
    Explanations

    code and numerical data

    oai_token-act-pair · gemini-2.0-flash

    Arabic characters

    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
     Efq
    -0.91
     itſelf
    -0.87
     purpoſe
    -0.78
     cauſe
    -0.71
    ſelf
    -0.71
     uſe
    -0.70
     himſelf
    -0.69
     themſelves
    -0.69
     reaſon
    -0.68
     Reſ
    -0.68
    POSITIVE LOGITS
     ل
    0.42
     من
    0.40
     و
    0.40
     وال
    0.39
     الم
    0.38
     س
    0.36
     ال
    0.36
     ن
    0.34
     ب
    0.33
     ا
    0.33
    Activations Density 1.096%

    No Known Activations