© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6580
    Prev
    Next
    INDEX
    Explanations

    phrases referencing authors and their writings

    oai_token-act-pair · gemini-2.0-flash

    Writing attribution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    mybatisplus
    -0.65
     ویکی‌پدیا
    -0.64
    StoreMessageInfo
    -0.63
     saites
    -0.61
     pleaſure
    -0.59
    
    -0.59
     NSCoder
    -0.57
    awtextra
    -0.57
    MANUFACT
    -0.56
    EndProject
    -0.55
    POSITIVE LOGITS
     co
    0.64
     ghost
    0.59
     contributed
    0.58
     contribute
    0.58
    новништво
    0.58
    ghost
    0.56
     contributes
    0.55
     fantasma
    0.54
     contributing
    0.54
     fantasmas
    0.54
    Activations Density 2.320%

    No Known Activations