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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14094
    Prev
    Next
    INDEX
    Explanations

    words dealing with mechanical, chemical, or electrical equipment.

    oai_token-act-pair · gemini-2.0-flash

    equipment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     equipment
    -1.77
     Equipment
    -1.49
    equipment
    -1.46
    Equipment
    -1.43
     EQUIPMENT
    -1.37
     gear
    -1.16
    EQUIPMENT
    -1.11
     hardware
    -1.06
     оборудования
    -1.05
     équipement
    -1.05
    POSITIVE LOGITS
    RuleContext
    0.65
     CreateTagHelper
    0.64
    kedés
    0.64
    Παραπομπές
    0.61
    Kjelder
    0.59
    jooq
    0.59
    userdetails
    0.59
    errHandler
    0.59
    ύν
    0.58
     Elek
    0.58
    Activations Density 10.992%

    No Known Activations