© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    arabic text within an english document

    oai_token-act-pair · gemini-2.0-flash

    Non-English text/code

    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
     karet
    -0.41
    ，
    -0.40
     kriminal
    -0.36
    。
    -0.34
    的
    -0.34
    σθαι
    -0.33
     kosme
    -0.33
    和
    -0.33
    之助
    -0.33
     RAL
    -0.32
    POSITIVE LOGITS
    +#+#
    0.32
     剪影
    0.30
     图解
    0.29
    
    0.29
    aarrggbb
    0.28
    آم
    0.27
    ExtendWith
    0.26
     例证
    0.26
    ران
    0.26
    طل
    0.25
    Activations Density 0.848%

    No Known Activations