© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 979
    Prev
    Next
    INDEX
    Explanations

    the "..." token, and possibly also find "apk" and "res"

    oai_token-act-pair · gemini-2.0-flash

    Ellipsis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    devServer
    -0.55
    natal
    -0.52
     кирпи
    -0.49
     Lover
    -0.48
     uuidv
    -0.48
    Spinach
    -0.47
    acaktır
    -0.47
    Lover
    -0.46
    مساعدة
    -0.45
    fabri
    -0.45
    POSITIVE LOGITS
    تقاوى
    1.06
     صوتيه
    0.96
    tagHelperRunner
    0.87
     NUKAT
    0.86
     ComVisible
    0.85
    Geplaatst
    0.84
     виправивши
    0.81
     MainAxisSize
    0.81
     NSCoder
    0.81
    AnchorStyles
    0.78
    Activations Density 2.168%

    No Known Activations