© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words that indicate a person, device, or action is doing something

    oai_token-act-pair · gemini-2.0-flash

    actions

    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
    UnusedPrivate
    -0.87
     Majefty
    -0.86
     Theſe
    -0.84
     chré
    -0.83
     themſelves
    -0.83
     Houſe
    -0.82
     houſe
    -0.78
    ########.
    -0.77
     propOrder
    -0.75
     Jefus
    -0.73
    POSITIVE LOGITS
     runs
    0.95
     builds
    0.90
     drives
    0.84
     plays
    0.83
     walks
    0.79
     flies
    0.79
     rises
    0.79
     cooks
    0.78
     lifts
    0.78
     moves
    0.77
    Activations Density 3.984%

    No Known Activations