© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5673
    Prev
    Next
    INDEX
    Explanations

    a few specific phrases, like "it is:" and "me too", and the string "an" preceded by "La" and "der"

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    CloseOperation
    -0.55
    TagHelpers
    -0.52
    preter
    -0.52
    ография
    -0.50
    /></
    -0.48
    gitto
    -0.47
    UObject
    -0.47
    />,
    -0.46
    jure
    -0.46
     F
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
     Partager
    0.66
     betweenstory
    0.63
     flotante
    0.63
     onData
    0.62
     Abonnez
    0.62
     autorytatywna
    0.61
    RegistryLite
    0.59
    IsContent
    0.59
     الحره
    0.59
    Activations Density 0.967%

    No Known Activations