© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11469
    Prev
    Next
    INDEX
    Explanations

    greetings in various languages, including French and Russian

    oai_token-act-pair · gemini-2.0-flash

    non-english greetings

    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
    •hello_world:278c2a25-8446-5049-a239-c74419102559
    Top frequency features for prompt

    No Comments

    Negative Logits
     ContentValues
    -0.68
    astify
    -0.66
     فريبيس
    -0.66
     beginnetje
    -0.62
     TestBed
    -0.62
    #+#
    -0.58
    BorderFactory
    -0.57
    BindView
    -0.57
    WebElementEntity
    -0.57
    ScopeManager
    -0.56
    POSITIVE LOGITS
    Hello
    1.04
     Hello
    0.99
     hello
    0.98
    Greetings
    0.90
    hello
    0.87
    HELLO
    0.83
    Salut
    0.81
    Heya
    0.81
    Howdy
    0.79
    Здравствуйте
    0.78
    Activations Density 0.345%

    No Known Activations