© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    a mix of function names and French/Slavic words, possibly related to communication

    oai_token-act-pair · gemini-2.0-flash

    code or non-english text

    np_max-act · gemini-2.0-flash

    call

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Efq
    -0.64
    клопе
    -0.63
     ergeben
    -0.59
    ██
    -0.58
    PyExc
    -0.55
    úrese
    -0.54
    troppo
    -0.54
     acrylique
    -0.53
     correctes
    -0.53
    inheritDoc
    -0.52
    POSITIVE LOGITS
     call
    2.55
     calls
    2.39
    Call
    2.34
     Call
    2.33
     CALL
    2.31
    call
    2.28
     calling
    2.19
    CALL
    2.19
     Calls
    2.16
    calls
    2.09
    Activations Density 0.353%

    No Known Activations