© 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. 9518
    Prev
    Next
    INDEX
    Explanations

    text resembling formal rules or guidelines, especially those governing online interactions

    oai_token-act-pair · gemini-2.0-flash

    code/technical text

    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
    ToAction
    -0.64
     Winaray
    -0.59
     quæ
    -0.57
    IndentedString
    -0.57
    MEMORANDUM
    -0.53
     saites
    -0.53
     EconPapers
    -0.52
    RenderAtEndOf
    -0.51
     дописавши
    -0.51
    jfree
    -0.51
    POSITIVE LOGITS
     newOwner
    0.46
     java
    0.44
    الإنجليزية
    0.44
    bukkit
    0.44
    ̸
    0.43
    ̯
    0.43
    nativeElement
    0.42
    (){}
    0.41
    Únete
    0.41
     ressource
    0.41
    Activations Density 28.101%

    No Known Activations