© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    varied phrases related to academic publications, contact information, and restaurant reviews

    oai_token-act-pair · gemini-2.0-flash

    Formal documents and emails

    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
     Anſ
    -0.85
     vícti
    -0.81
     vérit
    -0.78
     cœurs
    -0.77
     tartalomajánló
    -0.77
     Reſ
    -0.75
     âmes
    -0.74
     épaules
    -0.74
     beſch
    -0.73
    tagHelperRunner
    -0.72
    POSITIVE LOGITS
     
    0.62
     that
    0.61
     the
    0.60
     there
    0.51
     this
    0.51
     these
    0.48
     a
    0.48
     as
    0.47
     for
    0.46
     “
    0.46
    Activations Density 10.981%

    No Known Activations