© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3055
    Prev
    Next
    INDEX
    Explanations

    salutations in different languages

    oai_token-act-pair · gemini-2.0-flash

    greetings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     оригіналу
    -0.97
    '},
    -0.90
    RenderAtEndOf
    -0.84
    +:+
    -0.83
    ")));
    -0.78
    تقاوى
    -0.77
    ьаж
    -0.77
    دانشنامهٔ
    -0.76
     viewDidLoad
    -0.75
    '])){
    -0.75
    POSITIVE LOGITS
    issi
    0.51
     waving
    0.46
    lepaskan
    0.41
     sal
    0.40
     Farewell
    0.40
     Goodbye
    0.39
     goodbye
    0.39
    messages
    0.38
    Bye
    0.38
    ami
    0.38
    Activations Density 0.708%

    No Known Activations