© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3091
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "is" or things that people want

    oai_token-act-pair · gemini-2.0-flash

    Personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     doPost
    -0.66
     [*]
    -0.54
    cach
    -0.51
     Ca
    -0.49
     vice
    -0.45
    ർ
    -0.45
    nsyn
    -0.45
     niên
    -0.44
    \}_{
    -0.44
     ات
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.77
    出版年
    0.77
    Geplaatst
    0.70
     estimés
    0.65
    tymologie
    0.63
     EconPapers
    0.62
    kháu
    0.62
     мѣ
    0.60
    Lähteet
    0.60
     Uniwersyte
    0.60
    Activations Density 2.259%

    No Known Activations