© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12028
    Prev
    Next
    INDEX
    Explanations

    opening lines with greetings, especially "Hi," as well as some additional interface words

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Hello
    -0.96
     Hello
    -0.92
    Hi
    -0.80
     hello
    -0.78
    hello
    -0.74
     Hi
    -0.71
    Привет
    -0.70
    Heya
    -0.63
    HELLO
    -0.63
    hi
    -0.61
    POSITIVE LOGITS
     للاسماء
    0.97
    parsedMessage
    0.69
     Wikidata
    0.63
     متعلقه
    0.62
    oules
    0.61
    yntaxException
    0.61
     Paglinawan
    0.61
    Autoritní
    0.61
    __":
    0.60
     INTERESAR
    0.60
    Activations Density 3.612%

    No Known Activations