© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3666
    Prev
    Next
    INDEX
    Explanations

    mentions of months, religious concepts, and reverence.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    Tikang
    -0.58
    ########.
    -0.52
    #+#
    -0.51
     Himo
    -0.50
     Paglinawan
    -0.49
    بوابة
    -0.48
    הערות
    -0.46
    Архівовано
    -0.46
    GeneratedCode
    -0.45
    "}")
    -0.45
    POSITIVE LOGITS
     niitä
    0.56
     lovingly
    0.54
    lesia
    0.52
    irvana
    0.51
     kepad
    0.50
    jstor
    0.50
    ALE
    0.50
    Thou
    0.48
     stanga
    0.48
    EClass
    0.48
    Activations Density 28.836%

    No Known Activations