© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2392
    Prev
    Next
    INDEX
    Explanations

    positive words related to hobbies, social gatherings, estate sales, and retail events.

    oai_token-act-pair · gemini-2.0-flash

    gatherings, meetings

    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
    GOTREF
    -0.65
     Monfieur
    -0.58
    ModelState
    -0.56
    ftagPool
    -0.54
    vum
    -0.52
    TagHelpers
    -0.52
     brano
    -0.52
     myſelf
    -0.52
     Diaries
    -0.51
    źć
    -0.51
    POSITIVE LOGITS
     conferences
    1.34
     conference
    1.15
     Conferences
    1.06
     events
    1.02
     event
    1.02
     convention
    0.96
     festivals
    0.96
     seminars
    0.96
     annual
    0.96
     meetings
    0.95
    Activations Density 7.931%

    No Known Activations