© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14733
    Prev
    Next
    INDEX
    Explanations

    words related to microcontrollers, serial communication via COM ports, and SCADA systems.

    oai_token-act-pair · gemini-2.0-flash

    communication

    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
    UnsafeEnabled
    -0.68
    ⓧ
    -0.63
    DeleteBehavior
    -0.61
    تفصیلات
    -0.59
    НИК
    -0.58
    EClass
    -0.57
    verifyException
    -0.57
    @[+][
    -0.56
    migrationBuilder
    -0.56
    SharedCtor
    -0.56
    POSITIVE LOGITS
     communication
    0.80
     communications
    0.75
     communicate
    0.74
     comms
    0.74
     communicating
    0.73
     Communication
    0.73
    COMMUNIC
    0.70
    Communication
    0.68
     communic
    0.66
     comunicación
    0.66
    Activations Density 3.814%

    No Known Activations