© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6334
    Prev
    Next
    INDEX
    Explanations

    the word "I" and "we" in the context of a discussion about past reading

    oai_token-act-pair · gemini-2.0-flash

    variations of "leave"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     saites
    -0.66
    webElementGuid
    -0.58
     ujednoznacz
    -0.53
    ритори
    -0.53
     кӀош
    -0.52
    ViewFeatures
    -0.51
     الحره
    -0.51
    verwijspagina
    -0.49
     '\\;'
    -0.49
     consumed
    -0.49
    POSITIVE LOGITS
     leaving
    1.62
     Leave
    1.61
     leave
    1.61
    Leave
    1.59
    leave
    1.55
     left
    1.45
     Leaving
    1.40
     LEAVE
    1.40
    leaving
    1.38
    Leaving
    1.31
    Activations Density 0.711%

    No Known Activations