© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12016
    Prev
    Next
    INDEX
    Explanations

    words, names, and terms related to wealthy people

    oai_token-act-pair · gemini-2.0-flash

    wealth and extravagance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     F
    -0.50
     Es
    -0.50
     Paglinawan
    -0.48
     es
    -0.44
     Sch
    -0.43
     K
    -0.42
    bes
    -0.41
     Multi
    -0.41
     sch
    -0.41
     e
    -0.40
    POSITIVE LOGITS
     pleaſure
    1.09
     itſelf
    1.05
     Monfieur
    1.04
     fhew
    1.03
     Jefus
    1.02
     صوتيه
    1.02
     purpoſe
    0.97
     Efq
    0.95
     myſelf
    0.94
     houſe
    0.93
    Activations Density 0.442%

    No Known Activations