© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4382
    Prev
    Next
    INDEX
    Explanations

    file headers and names containing "probe", "trace", "event", "core", "build", "debug", and "system"

    oai_token-act-pair · gemini-2.0-flash

    probe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    SHEET
    -1.00
    FREQUENCY
    -0.96
    CAPACITY
    -0.94
    TASKS
    -0.91
    PANEL
    -0.90
    CONTROLLER
    -0.89
    SELECTION
    -0.88
    NODES
    -0.87
    DAMAGE
    -0.87
    CHANNELS
    -0.87
    POSITIVE LOGITS
    GEBURTSDATUM
    0.96
    IMPORTED
    0.84
    ID
    0.83
    OPP
    0.79
    XD
    0.78
    IS
    0.77
    PS
    0.77
     TMP
    0.75
    NT
    0.75
    NP
    0.75
    Activations Density 2.386%

    No Known Activations