© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5573
    Prev
    Next
    INDEX
    Explanations

    words ending in "an" and other seemingly random words, with a very strong activation when it encounters the sequence "$@".

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyTitle
    -0.58
    aarrggbb
    -0.57
     سكانية
    -0.54
    richTextPanel
    -0.51
    )"),
    -0.50
     Baillargeon
    -0.50
     raiſ
    -0.50
     EconPapers
    -0.49
    LEncoder
    -0.49
    IntoConstraints
    -0.48
    POSITIVE LOGITS
     jambes
    0.80
     opinião
    0.79
     renseignements
    0.79
     démocr
    0.78
     elä
    0.77
     duração
    0.76
     samfun
    0.76
     travailleurs
    0.76
     pensieri
    0.76
     marquées
    0.76
    Activations Density 4.097%

    No Known Activations