© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7521
    Prev
    Next
    INDEX
    Explanations

    code in various languages

    oai_token-act-pair · gemini-2.0-flash

    prostitution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     btn
    -0.68
     BorderRadius
    -0.64
     CGRect
    -0.60
     onPage
    -0.60
     url
    -0.60
     CURLOPT
    -0.59
     std
    -0.59
     awakeFromNib
    -0.58
     doPost
    -0.58
     bool
    -0.57
    POSITIVE LOGITS
     prostitu
    0.60
     carnaval
    0.54
     pleaſure
    0.54
     themſelves
    0.53
     peniten
    0.49
     Protestantism
    0.49
     alcoholism
    0.48
     himſelf
    0.48
     prostitution
    0.48
     palme
    0.48
    Activations Density 9.945%

    No Known Activations