© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6408
    Prev
    Next
    INDEX
    Explanations

    words relating to restaurants and food, particularly fancy foods and French cuisine.

    oai_token-act-pair · gemini-2.0-flash

    cuts of beef

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PendingIntent
    -0.65
     typelib
    -0.65
    TypedDataSet
    -0.64
    ResumeLayout
    -0.59
    BASEPATH
    -0.58
    AccessorTable
    -0.58
     Glor
    -0.57
    WebControls
    -0.57
    ngrx
    -0.57
    PerformLayout
    -0.56
    POSITIVE LOGITS
     cuts
    0.60
     flank
    0.57
     sir
    0.56
    Sir
    0.54
     Angus
    0.53
     cortes
    0.53
     Kobe
    0.52
     Cuts
    0.52
     prime
    0.51
     angus
    0.50
    Activations Density 0.946%

    No Known Activations