© 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. 1828
    Prev
    Next
    INDEX
    Explanations

    single character tokens appearing alongside periods, apostrophes and the word loved

    oai_token-act-pair · 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
    being
    -1.24
     being
    -1.23
    Being
    -0.98
     BEING
    -0.98
     Being
    -0.91
     siendo
    -0.80
     working
    -0.80
    having
    -0.79
     having
    -0.77
     getting
    -0.76
    POSITIVE LOGITS
    XmlEnum
    0.60
     CreateTagHelper
    0.50
    Autowired
    0.48
    TestingModule
    0.47
    principalTable
    0.46
    ()?;
    0.46
     فريبيس
    0.46
    tizia
    0.44
     setuptools
    0.44
    TabbedPane
    0.43
    Activations Density 4.504%

    No Known Activations