© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11675
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly random words when they are adjacent to words written with diacritics, non-English punctuation, or capitalization in an unusual location

    oai_token-act-pair · gemini-2.0-flash

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    رشف
    -0.77
     >=",
    -0.69
    Jereo
    -0.66
    SequentialGroup
    -0.65
     Chwiliwch
    -0.62
    évaluateur
    -0.61
     autorytatywna
    -0.59
    AllAfrica
    -0.57
    قایناق‌لار
    -0.57
    sizeCache
    -0.56
    POSITIVE LOGITS
    di
    0.82
    ding
    0.82
    da
    0.80
    dy
    0.75
    dies
    0.74
    ida
    0.69
    ides
    0.69
    die
    0.67
    ded
    0.67
    idi
    0.66
    Activations Density 0.583%

    No Known Activations